© 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 EvalsExportsinterp-engineNEWAPI 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. 7-RESID-POST-AA
    11. 10803
    Prev
    Next
    INDEX
    Explanations

    scripts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    払い
    -0.07
    只能说
    -0.07
    изм
    -0.07
     haya
    -0.07
    同比增长
    -0.07
     verifies
    -0.06
    ũng
    -0.06
    ük
    -0.06
    𠅤
    -0.06
     обязательно
    -0.06
    POSITIVE LOGITS
     буд
    0.08
     Maced
    0.07
    _KEYWORD
    0.07
    \Module
    0.07
    _LOOP
    0.07
    yled
    0.07
     OCC
    0.06
     spir
    0.06
    _npc
    0.06
    _pipeline
    0.06
    Activations Density 0.106%

    No Known Activations