© 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. 30730
    Prev
    Next
    INDEX
    Explanations

    steps, process, documentation

    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
    _INFORMATION
    -0.08
    ãĥªãĥĥãĥĹ
    -0.08
    oho
    -0.08
     seger
    -0.08
    /dist
    -0.08
    leftright
    -0.08
    æŶæĹł
    -0.08
    amani
    -0.08
     Kenntnis
    -0.08
    使åĩº
    -0.08
    POSITIVE LOGITS
    æ¯ıä¸ĢæŃ¥
    0.13
    æŃ¥éª¤
    0.12
    ä¸ĢæŃ¥ä¸ĢæŃ¥
    0.11
     steps
    0.11
    ä¸ĢæŃ¥æŃ¥
    0.11
    è¿ĩç¨ĭ
    0.10
     step
    0.10
    è¿ĩç¨ĭçļĦ
    0.10
     process
    0.09
    è¿ĩç¨ĭåĴĮ
    0.09
    Activations Density 0.052%

    No Known Activations