© 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. 3336
    Prev
    Next
    INDEX
    Explanations

    results, meta, runner, best, examples, solve

    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
    ocs
    -0.08
    conde
    -0.07
    à°Ń
    -0.07
    odb
    -0.07
    çek
    -0.07
    /util
    -0.07
    ç©Į
    -0.06
    tof
    -0.06
    天é¾Ļ
    -0.06
     hyp
    -0.06
    POSITIVE LOGITS
    çī¹åĪ«æıIJéĨĴ
    0.07
    ETS
    0.07
    aum
    0.07
     übrigens
    0.07
    enal
    0.06
    çĶ¨åĪĢ
    0.06
    è¦ģ注æĦıçļĦæĺ¯
    0.06
    halt
    0.06
    ¤íĮ
    0.06
    ERC
    0.06
    Activations Density 0.014%

    No Known Activations