© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 29712
    Prev
    Next
    INDEX
    Explanations

    programming interface declarations

    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
    mula
    -0.08
    äºŃ
    -0.07
    .Msg
    -0.07
    æ½¢
    -0.07
    åİħéķ¿
    -0.07
    figur
    -0.07
    ä¸įåħ¨
    -0.07
    гÑĥÑĢ
    -0.07
    å¿«ç©¿
    -0.07
    ç®±
    -0.07
    POSITIVE LOGITS
    atte
    0.07
    æĦŁæģ©çļĦå¿ĥ
    0.07
    ussen
    0.06
    خة
    0.06
     Poke
    0.06
    طة
    0.06
    ÑĪеÑĢ
    0.06
    以å¤ĩ
    0.06
     Mate
    0.06
    大西æ´ĭ
    0.06
    Activations Density 0.012%

    No Known Activations