© 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. 1487
    Prev
    Next
    INDEX
    Explanations

    patent citations

    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
    OrDefault
    -0.07
    åı¯æ¢¦
    -0.07
    tempts
    -0.07
    owering
    -0.07
    _fake
    -0.07
    aring
    -0.07
    atable
    -0.07
    OGO
    -0.07
    åŁİ主
    -0.07
    quo
    -0.07
    POSITIVE LOGITS
    麾
    0.07
    Ùĥرة
    0.07
    åģļ大
    0.06
    acu
    0.06
     $__
    0.06
    __
    0.06
    éĻIJãĤĬ
    0.06
    Bud
    0.06
    .messaging
    0.06
    igheden
    0.06
    Activations Density 0.017%

    No Known Activations