© 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. 57136
    Prev
    Next
    INDEX
    Explanations

    price is $

    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
    !/
    -0.07
    å¿ĥçIJĨç´łè´¨
    -0.06
    otrop
    -0.06
    å¿
    -0.06
    enda
    -0.06
    èµ·åı¸
    -0.06
    æĸ¹éĿ¢
    -0.06
    ocha
    -0.06
    aoke
    -0.06
    uden
    -0.06
    POSITIVE LOGITS
    .gg
    0.08
    彪
    0.07
    ÑĪи
    0.07
    енÑĤÑı
    0.07
    说æľī
    0.07
    TB
    0.07
    strup
    0.07
    isd
    0.07
    rž
    0.07
    PAS
    0.07
    Activations Density 0.139%

    No Known Activations