© 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. 26551
    Prev
    Next
    INDEX
    Explanations

    Chinese herbal medicine ingredients

    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
    èij©
    -0.09
    åİħ
    -0.08
    _EXECUTE
    -0.08
    æµ·çĩķ
    -0.08
    cese
    -0.08
    uate
    -0.08
    åİ»ä½ķ
    -0.08
    à¹Ģà¸Ķà¹ĩà¸Ķ
    -0.08
    lessly
    -0.08
    Dispose
    -0.08
    POSITIVE LOGITS
    æ»ĭåħ»
    0.08
    æī¶
    0.07
    人åıĤ
    0.07
    è¡¥æ°Ķ
    0.07
     strength
    0.07
    è¿ĩ头
    0.07
     boost
    0.07
    çĽĬæ°Ķ
    0.07
     (++
    0.07
    ery
    0.07
    Activations Density 0.009%

    No Known Activations