© 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. 75373
    Prev
    Next
    INDEX
    Explanations

    commitment

    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
     gear
    -0.07
    grese
    -0.07
    惑
    -0.07
    вис
    -0.07
    體驗
    -0.07
     créer
    -0.07
    nst
    -0.07
     unintended
    -0.07
    anges
    -0.06
    編
    -0.06
    POSITIVE LOGITS
     commitment
    0.09
    =((
    0.09
    拉动
    0.08
    𬭊
    0.07
    /stretch
    0.07
    (Y
    0.07
     мобиль
    0.07
     brutal
    0.07
     Steelers
    0.06
     além
    0.06
    Activations Density 0.013%

    No Known Activations