© 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. 1100
    Prev
    Next
    INDEX
    Explanations

    in the matter of

    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
    igm
    -0.07
    æ¸ł
    -0.07
    led
    -0.07
    ëłĪ
    -0.07
    è´
    -0.06
     Jok
    -0.06
    书éĿ¢
    -0.06
     Leone
    -0.06
    æľīæĽ´å¥½çļĦ
    -0.06
     ado
    -0.06
    POSITIVE LOGITS
    纯粹
    0.10
    纯粹çļĦ
    0.10
    Pure
    0.09
    纯
    0.09
     Pure
    0.09
    pure
    0.08
    åŀĭ
    0.08
    ç´Ķ
    0.08
    ç±»
    0.08
    æĪijåıªæĥ³
    0.08
    Activations Density 0.311%

    No Known Activations