© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 80433
    Prev
    Next
    INDEX
    Explanations

    first

    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
    Negative Logits
    _offer
    -0.07
    -tooltip
    -0.07
    خب
    -0.07
     Conference
    -0.06
    ادات
    -0.06
     ridicule
    -0.06
    _tooltip
    -0.06
     disdain
    -0.06
    <?
    -0.06
    @param
    -0.06
    POSITIVE LOGITS
    ימי
    0.07
    ちゃ
    0.07
    馈
    0.07
     tendencies
    0.07
     DropIndex
    0.07
    entities
    0.07
    饼干
    0.06
     faker
    0.06
     routes
    0.06
     הי
    0.06
    Activations Density 0.049%

    No Known Activations