© 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. 45322
    Prev
    Next
    INDEX
    Explanations

    Lyapunov exponent analysis

    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
    å¿ħ须注æĺİ
    -0.07
    tene
    -0.07
    é«ĺåĵģè´¨çļĦ
    -0.07
    plen
    -0.07
    гоÑĢа
    -0.06
    ữa
    -0.06
    æĪij家çļĦ
    -0.06
    éĶĢ
    -0.06
    fre
    -0.06
    ç±³çļĦ
    -0.06
    POSITIVE LOGITS
    Reviewer
    0.08
    apun
    0.08
    evaluate
    0.07
    çĿ¦
    0.07
     evaluations
    0.07
     evaluating
    0.07
    ordes
    0.07
    ANGO
    0.07
    avia
    0.07
    caret
    0.07
    Activations Density 0.001%

    No Known Activations