© 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. 43757
    Prev
    Next
    INDEX
    Explanations

    superscript 2

    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
    æĢİä¹ĪäºĨ
    -0.07
    Fullscreen
    -0.07
    家éŨ
    -0.06
    stras
    -0.06
    磨çģŃ
    -0.06
    çŃ·
    -0.06
    åĪ°æł¡
    -0.06
    éĿ¢é£Ł
    -0.06
    家éŨåı£
    -0.06
    rud
    -0.06
    POSITIVE LOGITS
    emi
    0.07
    yron
    0.07
    éch
    0.07
    -guard
    0.07
    mart
    0.06
    atis
    0.06
    ildir
    0.06
    éĩijåŃIJ
    0.06
    weisung
    0.06
    clair
    0.06
    Activations Density 0.002%

    No Known Activations