© 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. 47123
    Prev
    Next
    INDEX
    Explanations

    coupled by

    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
    å¥Ĺ
    -0.06
    å¤±æľĽ
    -0.06
     values
    -0.06
    olk
    -0.06
    è¿İéĿ¢
    -0.06
    ä»ĭ
    -0.06
     ting
    -0.05
    ä»°
    -0.05
     decl
    -0.05
    ç¸
    -0.05
    POSITIVE LOGITS
     additions
    0.09
    è°´
    0.09
     cód
    0.09
    opan
    0.09
    odio
    0.09
     staples
    0.08
    _modified
    0.08
    ä¸Ģæī«
    0.08
    ampp
    0.08
    धान
    0.08
    Activations Density 0.012%

    No Known Activations