© 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. 20767
    Prev
    Next
    INDEX
    Explanations

    word fragments and file extensions

    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
     tie
    -0.07
    ÑĢеб
    -0.07
    ÙĪبÙĬ
    -0.07
    åIJİæīį
    -0.06
    uels
    -0.06
    _FOREACH
    -0.06
    nton
    -0.06
    engan
    -0.06
    RSS
    -0.06
    chand
    -0.06
    POSITIVE LOGITS
    ç½Ħ
    0.08
    hluk
    0.07
     Tits
    0.07
     ìĭłê²½
    0.06
    è¿Ļæł·ä¸ĢæĿ¥
    0.06
    è¼Ŀ
    0.06
    dad
    0.06
    acon
    0.06
    åĸ±
    0.06
    è¾ī
    0.06
    Activations Density 0.046%

    No Known Activations