© 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. 45206
    Prev
    Next
    INDEX
    Explanations

    community, support, and shared resources

    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
    非物质
    -0.07
     Partner
    -0.07
    严厉打击
    -0.07
     supplements
    -0.06
    .dumps
    -0.06
    orget
    -0.06
     Matters
    -0.06
    ){↵
    -0.06
    ߍ
    -0.06
     amendment
    -0.06
    POSITIVE LOGITS
    敏捷
    0.07
     각
    0.07
    cona
    0.07
     pesticide
    0.06
    Structured
    0.06
     Wert
    0.06
     scent
    0.06
     segregated
    0.06
    accès
    0.06
    켓
    0.06
    Activations Density 1.996%

    No Known Activations