© 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. 7677
    Prev
    Next
    INDEX
    Explanations

    from

    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
     fascism
    -0.07
     torture
    -0.07
    distribution
    -0.07
    מועצה
    -0.07
    CID
    -0.07
    Visitor
    -0.06
     tavern
    -0.06
    eses
    -0.06
     lazy
    -0.06
     UserId
    -0.06
    POSITIVE LOGITS
    了一份
    0.07
    能达到
    0.07
    越好
    0.07
    ')}</
    0.07
    Alex
    0.07
    .manager
    0.07
    Meanwhile
    0.06
    _level
    0.06
    ◞
    0.06
     attorneys
    0.06
    Activations Density 0.110%

    No Known Activations