© 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. 32323
    Prev
    Next
    INDEX
    Explanations

    in-house software, occupied, fiscal year, services

    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
    ä¸įæķ£
    -0.08
    è°ĥçłĶåijĺ
    -0.08
     confron
    -0.08
    ä¸įè¿ĩæĿ¥
    -0.08
    çŁ³æĻ¯
    -0.07
    è²¢
    -0.07
    å·¡è§Ĩåijĺ
    -0.07
    illons
    -0.07
    æĭĽèģĺåįķä½į
    -0.07
    catid
    -0.07
    POSITIVE LOGITS
    ç»ıæŁ¥
    0.09
    ä¼ļè®¡æł¸ç®Ĺ
    0.07
    æĮīè§Ħå®ļ
    0.07
    æľīä¸ĭåĪĹ
    0.07
    è´Ńè¿Ľ
    0.07
    åįĹåĽ½
    0.07
     taxable
    0.07
    ä¸ŃéĢĶ
    0.07
    æŁ¥æĺİ
    0.07
    ours
    0.07
    Activations Density 0.003%

    No Known Activations