© 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. 75188
    Prev
    Next
    INDEX
    Explanations

    try

    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
     precinct
    -0.08
    ﴀ
    -0.07
     flashed
    -0.07
     lyr
    -0.07
     sympathetic
    -0.07
     personalities
    -0.07
     expenditure
    -0.07
    ENU
    -0.07
     Buf
    -0.07
     cartridge
    -0.07
    POSITIVE LOGITS
     있으며
    0.07
    ないこと
    0.07
    옅
    0.07
    长得
    0.07
    탔
    0.07
    .getChildren
    0.07
     anything
    0.07
    ありがとう
    0.07
    ((((
    0.07
     Honey
    0.07
    Activations Density 0.002%

    No Known Activations