© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 3271
    Prev
    Next
    INDEX
    Explanations

    design and consulting

    np_max-act · gemini-2.0-flash

    Technical descriptions of experimental methods, apparatus and numeric specifications (measurements, equipment setup, and related procedural details).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    펑
    -0.07
    .AutoScaleMode
    -0.07
     compens
    -0.07
    interpreter
    -0.07
     livest
    -0.06
    -python
    -0.06
     Knowledge
    -0.06
    .readdir
    -0.06
    ようと
    -0.06
     accompagn
    -0.06
    POSITIVE LOGITS
    лей
    0.07
    quals
    0.07
     Phi
    0.07
    _high
    0.07
     fos
    0.07
    кой
    0.06
     oui
    0.06
    的眼
    0.06
     chars
    0.06
    곰
    0.06
    Activations Density 1.275%

    No Known Activations