© 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. 63456
    Prev
    Next
    INDEX
    Explanations

    laughter and exclamations

    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
    hq
    -0.08
    ç½
    -0.08
    রণ
    -0.08
    ICI
    -0.07
    qed
    -0.07
    izont
    -0.07
    øm
    -0.07
     Lexer
    -0.07
    æľĽ
    -0.07
    antara
    -0.07
    POSITIVE LOGITS
    aldi
    0.07
    æľº
    0.07
    ä¸Ģæĸ°
    0.07
    zia
    0.07
    ,,
    0.07
    åıĪ被
    0.06
    ©
    0.06
    orse
    0.06
     Sutton
    0.06
    ih
    0.06
    Activations Density 0.131%

    No Known Activations