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. 1757
    Prev
    Next
    INDEX
    Explanations

    Statistical values

    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
    愿景
    -0.07
    ottesville
    -0.07
    ERRUPT
    -0.07
    elas
    -0.07
    ----↵
    -0.06
    扫黑除
    -0.06
    'h
    -0.06
    Tpl
    -0.06
    egis
    -0.06
    ѕ
    -0.06
    POSITIVE LOGITS
     직접
    0.09
     Detroit
    0.07
    があった
    0.07
     residents
    0.07
    .Single
    0.07
    𨱇
    0.07
     lizard
    0.07
    _street
    0.06
    _whitespace
    0.06
    _special
    0.06
    Activations Density 0.012%

    No Known Activations