© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 17670
    Prev
    Next
    INDEX
    Explanations

    Hawking, King, shock

    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
    -toggle
    -0.07
    å®ľæĺ¥
    -0.07
    artis
    -0.07
    ниÑĩеÑģÑĤво
    -0.06
    ä¸įèī¯
    -0.06
    ãģ©ãģĵãĤį
    -0.06
    èĢħåı¯
    -0.06
    raquo
    -0.06
    è¿Ŀåıįä¸Ĭè¿°
    -0.06
    urar
    -0.06
    POSITIVE LOGITS
    æĶ¯ä»ĺç»Ļ
    0.07
    硬件
    0.07
     imminent
    0.07
    uele
    0.07
    åĨ·æ°Ķ
    0.07
    ĥģ
    0.07
    pone
    0.06
    oces
    0.06
    ForObject
    0.06
    órica
    0.06
    Activations Density 0.002%

    No Known Activations