© 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. 15-RESID-POST-AA
    11. 125911
    Prev
    Next
    INDEX
    Explanations

    :

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     discussed
    -0.07
     Tro
    -0.07
    _PT
    -0.07
     suggesting
    -0.07
     Te
    -0.07
    耶�
    -0.07
     Sr
    -0.07
     ${
    -0.06
     Religious
    -0.06
     insign
    -0.06
    POSITIVE LOGITS
    .INPUT
    0.08
    仓位
    0.07
    эм
    0.07
    .goal
    0.07
    נקוד
    0.07
     emoji
    0.07
    青
    0.07
    .Monad
    0.07
    =end
    0.06
    一家
    0.06
    Activations Density 0.012%

    No Known Activations