© 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. 26075
    Prev
    Next
    INDEX
    Explanations

    javascript file extensions

    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
    en
    -0.07
    ode
    -0.07
    EN
    -0.06
    ä½ĵç³»çļĦ
    -0.06
     Leip
    -0.06
    oc
    -0.06
    YA
    -0.06
    ra
    -0.06
    åľ¨åĽ½å®¶
    -0.06
     dummy
    -0.06
    POSITIVE LOGITS
    irit
    0.08
    OPSIS
    0.07
    GenericType
    0.07
    elaar
    0.07
    nard
    0.07
    entif
    0.07
    AsyncResult
    0.07
    -anchor
    0.07
    æľĢæĸ°æĸĩç«ł
    0.07
    æ§Ľ
    0.07
    Activations Density 0.015%

    No Known Activations