© 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. 82628
    Prev
    Next
    INDEX
    Explanations

    Racing/Championships

    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
     ter
    -0.07
    -per
    -0.07
     Joan
    -0.06
     Odyssey
    -0.06
     Purdue
    -0.06
    reservation
    -0.06
    over
    -0.06
     Lehr
    -0.06
    ynchronization
    -0.06
     �
    -0.06
    POSITIVE LOGITS
    微量
    0.07
    _TURN
    0.07
    ATUS
    0.07
    -flat
    0.07
    对我来说
    0.07
    PKG
    0.07
    箖
    0.07
    _point
    0.07
    .sendKeys
    0.07
    BI
    0.07
    Activations Density 0.091%

    No Known Activations