© 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. 11-RESID-POST-AA
    11. 22530
    Prev
    Next
    INDEX
    Explanations

    Stevens-Johnson syndrome

    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
     Remain
    -0.07
     shuffle
    -0.07
    .Api
    -0.07
    本当に
    -0.06
    -node
    -0.06
    .union
    -0.06
    ✨
    -0.06
    ථ
    -0.06
     auth
    -0.06
    =%.
    -0.06
    POSITIVE LOGITS
    erton
    0.07
    ︹
    0.07
    tica
    0.07
    _COST
    0.07
     basic
    0.07
    تكنولوجيا
    0.07
    .uml
    0.07
    yscale
    0.06
    Studio
    0.06
    毌
    0.06
    Activations Density 0.038%

    No Known Activations