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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 15-RESID-POST-AA
    6. 16654
    Prev
    Next
    INDEX
    Explanations

    elevation

    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
     Jean
    -0.07
    ổ
    -0.07
     Northwest
    -0.06
    尽管
    -0.06
    inox
    -0.06
    !!↵↵
    -0.06
     sü
    -0.06
    /fast
    -0.06
    unist
    -0.06
    POSITIVE LOGITS
    Attendance
    0.08
    ᐅ
    0.07
    🍈
    0.07
    .DataAnnotations
    0.07
    多项
    0.07
    榛
    0.07
    专家
    0.07
     humility
    0.07
     shaped
    0.07
    EntityType
    0.07
    Activations Density 0.005%

    No Known Activations