© 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. 45702
    Prev
    Next
    INDEX
    Explanations

    example code snippets

    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
    aru
    -0.07
    æ·±èĵĿ
    -0.07
    ä¸Ģæĸ°
    -0.06
    /
    -0.06
    åIJģ
    -0.06
    rost
    -0.06
    å¾Ĵ
    -0.06
    ur
    -0.06
    olist
    -0.06
    ×ķ×ĵ
    -0.06
    POSITIVE LOGITS
    ÑĢей
    0.09
     ÑģиÑĤÑĥ
    0.08
     Situation
    0.08
    çļĦæĥħæĻ¯
    0.07
    èµ°å¾Ĺ
    0.07
    çļĦæĥħ
    0.07
     ÎŃÏĩ
    0.07
    à¸ģà¸ĩ
    0.07
    stras
    0.07
    ression
    0.07
    Activations Density 0.002%

    No Known Activations