© 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. 20929
    Prev
    Next
    INDEX
    Explanations

    output parameter types

    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
    èµĦæºIJçļĦ
    -0.07
    igm
    -0.07
     Cong
    -0.07
    bard
    -0.07
    ä¸įåı¯
    -0.07
    ä¸ĩå¹´
    -0.06
    pard
    -0.06
    Å¡k
    -0.06
    äº
    -0.06
    ÃŃd
    -0.06
    POSITIVE LOGITS
     /^[
    0.08
    æķı
    0.08
     tâ
    0.07
    说èĩªå·±
    0.07
    Ľ
    0.07
     minlength
    0.07
    å®ŀè·µèĥ½åĬĽ
    0.07
    éĽ¹
    0.07
    å±¥è¡Į
    0.07
     fulfilling
    0.07
    Activations Density 0.015%

    No Known Activations