© 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. 3522
    Prev
    Next
    INDEX
    Explanations

    numbers after the

    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
    bas
    -0.08
    Bas
    -0.07
    ieni
    -0.07
    åĽ´
    -0.06
    åįķä½į
    -0.06
    æĿı
    -0.06
    主è¦ģæĺ¯
    -0.06
    æł¸
    -0.06
    lant
    -0.06
     helst
    -0.06
    POSITIVE LOGITS
    è°ħ
    0.08
    æ¶ĪæĿĢ
    0.07
    ìĤ
    0.07
    èĭ±æĸĩåIJįåŃĹ
    0.07
    ä¸İ家éķ¿
    0.07
    壮大çļĦ
    0.07
    å°±ç»ĵæĿŁäºĨ
    0.07
    .Atomic
    0.07
    è¯Ħè®®
    0.07
    <D
    0.07
    Activations Density 0.002%

    No Known Activations