© 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. 25458
    Prev
    Next
    INDEX
    Explanations

    vote Flake for U.S. Senate

    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
    æ¯ĶæĻ®éĢļ
    -0.09
     multiplying
    -0.07
    ink
    -0.06
    éĢ
    -0.06
    åĮªæµħ
    -0.06
     multiplication
    -0.06
    ä¾Ī
    -0.06
    /connection
    -0.06
     intimate
    -0.06
    _modify
    -0.06
    POSITIVE LOGITS
     choice
    0.09
    åģı好
    0.08
    å¿ħèĥľ
    0.08
    éĢīæĭ©çļĦ
    0.08
    å¤ĩéĢī
    0.08
    ÙĬÙĨÙĩ
    0.08
     whichever
    0.08
     selections
    0.08
    Selection
    0.08
    éĢīæĭ©
    0.08
    Activations Density 0.028%

    No Known Activations