© 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. 13937
    Prev
    Next
    INDEX
    Explanations

    under one

    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
    èº
    -0.09
     Depor
    -0.09
    ħ
    -0.08
    综
    -0.08
    交éĢļèŃ¦å¯Ł
    -0.08
     ÑģмоÑĤÑĢе
    -0.08
    abyrinth
    -0.08
    Ale
    -0.07
    /sbin
    -0.07
    ullets
    -0.07
    POSITIVE LOGITS
    çłģ
    0.06
     codes
    0.06
     bed
    0.06
     Du
    0.06
    ä¸įå¾Ĺ
    0.06
    åģ¥åº·çłģ
    0.05
     sh
    0.05
    é£İå°ĺ
    0.05
     ch
    0.05
    çļĦä¸Ģç¬Ķ
    0.05
    Activations Density 0.001%

    No Known Activations