© 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. 11-RESID-POST-AA
    11. 5482
    Prev
    Next
    INDEX
    Explanations

    Code imports/includes

    np_max-act · gemini-2.0-flash

    programming-source file headers and top-of-file code metadata (license/copyright lines, import/include/pragma and similar directives).

    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
     Develop
    -0.07
    .mon
    -0.07
    	FOR
    -0.07
    皇宫
    -0.07
     laat
    -0.07
    完成
    -0.07
    _now
    -0.06
     состоя
    -0.06
    现金
    -0.06
    _AUD
    -0.06
    POSITIVE LOGITS
    宝石
    0.07
     glove
    0.07
     aberr
    0.07
     özgü
    0.07
    חבל
    0.07
    "),"
    0.06
    crop
    0.06
     설치
    0.06
    colors
    0.06
    娑
    0.06
    Activations Density 0.152%

    No Known Activations