© 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. 30906
    Prev
    Next
    INDEX
    Explanations

    or and

    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
    plast
    -0.08
    ıld
    -0.07
    evil
    -0.07
    ITHER
    -0.07
     Royale
    -0.07
    elize
    -0.07
    aeda
    -0.07
    odate
    -0.06
    Canceled
    -0.06
    ä¸ŃåįĹ
    -0.06
    POSITIVE LOGITS
    /or
    0.09
    oren
    0.08
     etc
    0.07
    phans
    0.07
    åĻ¨çŃī
    0.07
    ako
    0.06
    ucar
    0.06
    ä¹Łè·Ł
    0.06
    ãģ¨ãĤĤè¨Ģ
    0.06
    sem
    0.06
    Activations Density 0.431%

    No Known Activations