© 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
    2. Qwen3.5-9B Base
    3. 15-QWENSCOPE-RES-64K
    4. 41059
    Prev
    Next
    INDEX
    Explanations

    technical problem discussions

    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
    èįĴ
    -0.08
    æķ´
    -0.07
    å¹¶åIJĮæĹ¶
    -0.07
    åĭ¢
    -0.07
    á»ĩn
    -0.07
    .DEBUG
    -0.07
    [current
    -0.07
    æĹłåı¯å¥Īä½ķ
    -0.07
    ев
    -0.07
    ç³Ļ
    -0.06
    POSITIVE LOGITS
    æĪĸæľįåĬ¡
    0.07
    æĪĸ对
    0.07
    rink
    0.07
    æĪĸå¤ļ个
    0.07
    IndexOf
    0.07
    è±Į
    0.06
    .getElement
    0.06
    ehme
    0.06
    alous
    0.06
    Harness
    0.06
    Activations Density 0.002%

    No Known Activations