© 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. 1066
    Prev
    Next
    INDEX
    Explanations

    mathematical operations and terms

    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
    _indent
    -0.07
    èªĵè¨Ģ
    -0.06
    unt
    -0.06
    èĢĮä¸Ķæĺ¯
    -0.06
     Ñĩа
    -0.06
    èĢĮä¸Ĭ
    -0.06
    æł¼
    -0.06
    'e
    -0.06
    æĮ½
    -0.06
     (/
    -0.06
    POSITIVE LOGITS
    å¿ħé¡»æľī
    0.11
     mesti
    0.10
    óc
    0.08
    æĪijä¸įè¦ģ
    0.08
    azine
    0.08
    å¿ħé¡»
    0.08
    å¿ħé¡»æĺ¯
    0.08
    ukkan
    0.08
    ayout
    0.08
    ertype
    0.08
    Activations Density 0.003%

    No Known Activations