© 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. 19282
    Prev
    Next
    INDEX
    Explanations

    numbers and equations

    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
    è¾Ħ
    -0.08
    ä¹ĭåĪĹ
    -0.07
    leys
    -0.06
    ä¸Ģå¦Ĥ
    -0.06
    à§įà¦Ł
    -0.06
    nä
    -0.06
    å¸Ń
    -0.06
    çļĦä¸Ģçŀ¬éĹ´
    -0.06
    çļĦä¸ĢéĿ¢
    -0.06
    ç»
    -0.06
    POSITIVE LOGITS
    ardt
    0.08
    rapper
    0.08
    inski
    0.08
    tus
    0.07
    [model
    0.07
    çĽijäºĭ
    0.07
    [ii
    0.07
    ä¹ı
    0.07
    ombo
    0.07
    æīĢåij¨
    0.07
    Activations Density 0.084%

    No Known Activations