© 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. 13530
    Prev
    Next
    INDEX
    Explanations

    www

    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
    resolver
    -0.08
    ä¸īéĿ¢
    -0.08
    ä¿Ŀè¯ģåħ¶
    -0.08
    osse
    -0.08
     Harbor
    -0.08
    aranya
    -0.08
    ARAN
    -0.08
    achim
    -0.07
    çļĦæĮĩ导
    -0.07
    ulfilled
    -0.07
    POSITIVE LOGITS
    -ish
    0.07
    çļĦä¸Ģç§į
    0.07
    å¦
    0.07
    ikian
    0.07
     ÑģвоеобÑĢаз
    0.07
     cierto
    0.06
    reiz
    0.06
     Tas
    0.06
    驯
    0.06
    æĪĸèĢħ说
    0.06
    Activations Density 0.014%

    No Known Activations