© 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. 39916
    Prev
    Next
    INDEX
    Explanations

    types of publications or documents

    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
    åįĬåĬŁ
    -0.07
    æģ°æģ°
    -0.07
    oseb
    -0.07
    æ³¢
    -0.07
    pot
    -0.07
    çĽĬ
    -0.06
    -floor
    -0.06
    åIJĮçIJĨ
    -0.06
    еÑĩ
    -0.06
    beck
    -0.06
    POSITIVE LOGITS
    çݰ代人
    0.07
    EMI
    0.07
    داÙĨ
    0.07
    geber
    0.07
    NESS
    0.07
    æĭŁå®ļ
    0.07
    irman
    0.07
    çİīçݯ
    0.07
    .ua
    0.07
    amd
    0.07
    Activations Density 0.002%

    No Known Activations