© 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. 39323
    Prev
    Next
    INDEX
    Explanations

    units of measurement

    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
    谨记
    -0.07
    æľīæĽ´å¥½çļĦ
    -0.07
     Deprecated
    -0.06
    amana
    -0.06
    ambil
    -0.06
     addTo
    -0.06
    åŁºäºİ
    -0.06
    Implicit
    -0.06
    adder
    -0.06
     Bold
    -0.06
    POSITIVE LOGITS
    CADE
    0.07
    è²¢
    0.07
    iza
    0.07
     przypad
    0.07
     Distr
    0.07
    æĬĺåIJĪ
    0.07
    àµģà´Ĥ
    0.06
    conds
    0.06
    izes
    0.06
    ¯
    0.06
    Activations Density 0.022%

    No Known Activations