© 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. 11196
    Prev
    Next
    INDEX
    Explanations

    change or addition

    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
    iej
    -0.08
    æ£ĺæīĭ
    -0.07
    æ¯ĶæĻ®éĢļ
    -0.07
    apid
    -0.07
    é¢Ĩå·¾
    -0.07
    æĪ·æĪ·
    -0.07
    .micro
    -0.07
    hin
    -0.07
    ä¸Ĭå¹´åIJĮæľŁ
    -0.07
    åݻ年åIJĮæľŁ
    -0.07
    POSITIVE LOGITS
     apapun
    0.08
     anything
    0.08
    æī©å±ķ
    0.08
    à¹ĥà¸Ķà¹Ĩ
    0.08
     outside
    0.08
     commentary
    0.08
    è¿ĩå¤ļçļĦ
    0.08
    åİ»æĥ³
    0.07
    -comment
    0.07
    unken
    0.07
    Activations Density 0.009%

    No Known Activations