© 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. 24771
    Prev
    Next
    INDEX
    Explanations

    dates and identifiers

    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
     Starr
    -0.08
    ubl
    -0.07
    vr
    -0.07
    ä¸Ģ空
    -0.07
    slash
    -0.06
     Gab
    -0.06
    .DOM
    -0.06
     Pob
    -0.06
     mest
    -0.06
    eno
    -0.06
    POSITIVE LOGITS
    lec
    0.08
    ÙĥÙĬØ©
    0.08
    bery
    0.07
     tadi
    0.07
    áĥļáĥĶ
    0.07
    lemn
    0.07
    æģŃåĸľä½ł
    0.07
    hyl
    0.07
    liers
    0.07
    åľ¨æĸ°çļĦä¸Ģå¹´éĩĮ
    0.07
    Activations Density 0.006%

    No Known Activations