© 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. 33767
    Prev
    Next
    INDEX
    Explanations

    there are unique possible

    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
    FromString
    -0.07
    _ut
    -0.07
    ä¸įèĻļ
    -0.07
    ritic
    -0.06
     Ridley
    -0.06
    anker
    -0.06
     uud
    -0.06
    Fallback
    -0.06
    æ¡ĶåŃIJ
    -0.06
    æīĢæľª
    -0.06
    POSITIVE LOGITS
    éĤ£ä½łå°±
    0.08
    æľīä¸įåIJĮ
    0.07
    avana
    0.07
    åĪĻåı¯ä»¥
    0.07
    ikh
    0.07
    éĤ£åı¯
    0.07
    éĤ£æĪijå°±
    0.07
    avar
    0.07
     infinitely
    0.07
    æĮ½åĽŀ
    0.07
    Activations Density 0.008%

    No Known Activations