© 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. 43436
    Prev
    Next
    INDEX
    Explanations

    buyang huanwu decoction

    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
    obet
    -0.07
    abus
    -0.07
     unins
    -0.06
    elang
    -0.06
    é³į
    -0.06
    åݨèīº
    -0.06
    νÏİ
    -0.06
    rotch
    -0.06
    å¹ħ
    -0.06
    rück
    -0.06
    POSITIVE LOGITS
    åĬłåĩı
    0.09
    ç»ıåħ¸çļĦ
    0.09
    åŁºç¡Ģä¸Ĭ
    0.08
    ä¸ºåŁºç¡Ģ
    0.08
    çļĦç»ıåħ¸
    0.08
    ç»ıåħ¸
    0.08
    ä¸ºåŁºç¡ĢçļĦ
    0.08
     classics
    0.08
    è§ģäºİ
    0.07
    adapt
    0.07
    Activations Density 0.013%

    No Known Activations