© 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. 1318
    Prev
    Next
    INDEX
    Explanations

    smallest value

    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
    é«ĺ大
    -0.09
    é«ĺèĢ¸
    -0.08
     high
    -0.08
    å¾Īé«ĺ
    -0.08
    豪
    -0.08
    é«ĺ大çļĦ
    -0.08
     (>
    -0.08
    æĽ´é«ĺ
    -0.08
     towering
    -0.08
    é«ĺåĩº
    -0.08
    POSITIVE LOGITS
    æĽ´ä½İ
    0.15
    è¿ľä½İäºİ
    0.15
    lowest
    0.15
    è¾ĥä½İ
    0.15
    çļĦä½İ
    0.14
    å¾Īä½İ
    0.14
     lowest
    0.14
     Lowest
    0.14
    è¶Ĭä½İ
    0.14
    æŀģä½İ
    0.14
    Activations Density 0.144%

    No Known Activations