© 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. 41801
    Prev
    Next
    INDEX
    Explanations

    what

    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
     beads
    -0.07
     Miguel
    -0.07
    מוג
    -0.07
    _CBC
    -0.07
    못
    -0.07
    _ct
    -0.07
    ImageButton
    -0.07
     Correction
    -0.07
     bases
    -0.07
    扽
    -0.07
    POSITIVE LOGITS
    经营模式
    0.07
     PACK
    0.07
    全方位
    0.07
    有助于
    0.07
    马克思
    0.07
     ASUS
    0.06
     fas
    0.06
    See
    0.06
    ữa
    0.06
    沃尔玛
    0.06
    Activations Density 0.056%

    No Known Activations