Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 41550
    Prev
    Next
    INDEX
    Explanations

    URLs and code

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    打扫
    -0.07
    ttp
    -0.07
    同意
    -0.07
    loud
    -0.07
     synt
    -0.07
     DEFAULT
    -0.07
    _FILE
    -0.07
    .types
    -0.07
    \Console
    -0.07
    WithEmailAndPassword
    -0.07
    POSITIVE LOGITS
     Jeb
    0.08
    🎋
    0.08
    三位一体
    0.07
    _usr
    0.07
    $is
    0.07
     comb
    0.07
    ))))↵
    0.07
     mínimo
    0.07
    brero
    0.07
     המקום
    0.07
    Activations Density 0.034%

    No Known Activations