© 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. 50503
    Prev
    Next
    INDEX
    Explanations

    Chambé or text capture

    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
     Bünd
    -0.08
    اÙħÙĬØ©
    -0.07
    ------+
    -0.07
    kün
    -0.07
     Flam
    -0.07
    IENT
    -0.07
    лÑİби
    -0.07
    anus
    -0.07
    thu
    -0.07
     {!
    -0.06
    POSITIVE LOGITS
    antal
    0.08
    天éªĦ
    0.07
    å¿«
    0.07
    OSC
    0.07
    åĽ´
    0.06
    بØŃ
    0.06
    ucher
    0.06
    ucch
    0.06
     Darling
    0.06
    /functions
    0.06
    Activations Density 0.085%

    No Known Activations