© 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. 58188
    Prev
    Next
    INDEX
    Explanations

    make or setup

    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
    apres
    -0.07
    ifs
    -0.07
    ç»ı缸åħ³éĥ¨éŨæī¹åĩĨ
    -0.07
    .forward
    -0.07
    éĽ³
    -0.07
    è§Ī
    -0.06
    è¿ľæľŁ
    -0.06
    ç»Ļ大家åĪĨ享
    -0.06
     Orchestra
    -0.06
    anter
    -0.06
    POSITIVE LOGITS
    éĢīæĭ©
    0.08
    éĢīæĭ©çļĦ
    0.08
    éĢīæĭ©ä¸į
    0.08
    æĸ¯åħĭ
    0.08
     chosen
    0.08
    è°ĥæķ´
    0.08
    éĢīæĭ©åĴĮ
    0.08
     choose
    0.07
     chois
    0.07
    éĢīæĭ©ä¸Ģ个
    0.07
    Activations Density 0.017%

    No Known Activations