© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 33760
    Prev
    Next
    INDEX
    Explanations

    exclamation and question marks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Guz
    -0.08
    æĪĸ以
    -0.08
     seiz
    -0.08
    æĪĸå¤ļ个
    -0.08
    رÙĪÛĮ
    -0.08
    -caret
    -0.08
    缴æİ¥æĪĸéĹ´æİ¥
    -0.08
    elas
    -0.08
    ardin
    -0.07
     patern
    -0.07
    POSITIVE LOGITS
    onne
    0.08
    ps
    0.07
    ç»Ļèĩªå·±çļĦ
    0.07
    µľ
    0.06
    款
    0.06
    erring
    0.06
    upy
    0.06
    cp
    0.06
    aps
    0.06
    jung
    0.06
    Activations Density 0.001%

    No Known Activations