© 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. 3040
    Prev
    Next
    INDEX
    Explanations

    prove that

    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
    çļĦ人è¿ĺ
    -0.08
    anic
    -0.07
    èĨ©
    -0.07
    管å±Ģ
    -0.07
    enarios
    -0.07
    epy
    -0.07
    ä¸Ĭæĸĩ
    -0.07
    ampp
    -0.07
    ä¸į说
    -0.07
    aldi
    -0.07
    POSITIVE LOGITS
    翱
    0.07
    æ¿
    0.07
    å²ģå²ģ
    0.06
    gra
    0.06
    itora
    0.06
    :M
    0.06
     necess
    0.06
    tora
    0.06
    eces
    0.06
    bie
    0.06
    Activations Density 0.060%

    No Known Activations