© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 123284
    Prev
    Next
    INDEX
    Explanations

    data file formats

    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
     ;;^
    -0.07
    召
    -0.07
    胸部
    -0.07
     thiếu
    -0.06
     chicago
    -0.06
    <Class
    -0.06
    SCRIPTION
    -0.06
     thighs
    -0.06
     counsel
    -0.06
    校
    -0.06
    POSITIVE LOGITS
     Robots
    0.09
    _atom
    0.09
    `;↵↵
    0.08
     pena
    0.08
    分かり
    0.07
    ત
    0.07
    (asset
    0.07
     inté
    0.07
     stayed
    0.07
    -tags
    0.07
    Activations Density 0.007%

    No Known Activations