© 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. 30419
    Prev
    Next
    INDEX
    Explanations

    section numbers like 08- or 18-

    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
    ç·Ĵ
    -0.07
    gle
    -0.07
    绪
    -0.07
    åı¦ä¸ĢåįĬ
    -0.07
    ç¼Ń
    -0.07
    enk
    -0.06
    verted
    -0.06
    ghi
    -0.06
    çļĦåij½è¿IJ
    -0.06
    gl
    -0.06
    POSITIVE LOGITS
    æĽ¦
    0.08
    asilan
    0.08
    -disabled
    0.08
    _ANDROID
    0.08
    /Edit
    0.07
    æľĪ度
    0.07
    eya
    0.07
     ìĩ
    0.07
    Ỽt
    0.07
    ctest
    0.07
    Activations Density 0.040%

    No Known Activations