© 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. 15-RESID-POST-AA
    11. 83046
    Prev
    Next
    INDEX
    Explanations

    Measuring liquids/cooking

    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
    Not in Any Lists

    No Comments

    Negative Logits
     dataset
    -0.07
    tensor
    -0.07
     formulated
    -0.07
     instantly
    -0.07
    $date
    -0.07
     cosplay
    -0.06
    :D
    -0.06
    𝕴
    -0.06
     WHO
    -0.06
    #
    -0.06
    POSITIVE LOGITS
    ",
↵
    0.07
     yakın
    0.07
     bicycles
    0.07
    Labor
    0.07
     nostro
    0.06
    Wildcard
    0.06
     sisters
    0.06
    렷
    0.06
     Liberties
    0.06
    做出
    0.06
    Activations Density 0.008%

    No Known Activations