© 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. 19-RESID-POST-AA
    11. 70265
    Prev
    Next
    INDEX
    Explanations

    Que

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ♾
    -0.08
    สอบ
    -0.08
     rocked
    -0.07
    טוב
    -0.07
    apiro
    -0.07
     QMap
    -0.07
     bun
    -0.07
     itm
    -0.07
    立ち
    -0.07
    ✿
    -0.07
    POSITIVE LOGITS
    -navigation
    0.07
    _types
    0.07
     Production
    0.07
    output
    0.07
     shoe
    0.07
     che
    0.07
    交
    0.07
    Handle
    0.07
    Share
    0.07
     que
    0.07
    Activations Density 0.010%

    No Known Activations