© 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. 32781
    Prev
    Next
    INDEX
    Explanations

    non-zero / null values

    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
    hammer
    -0.08
    ØŃÙĦ
    -0.07
     سÙĦ
    -0.07
    讼
    -0.07
    æģ¬
    -0.07
    _translate
    -0.07
    ince
    -0.07
     NEXT
    -0.07
    erm
    -0.07
     Liebl
    -0.07
    POSITIVE LOGITS
     ненÑĥ
    0.10
    NotEmpty
    0.08
    /non
    0.08
    饱满
    0.08
    nonnull
    0.07
     nonzero
    0.07
    éĤ£é¢Ĺ
    0.07
    idable
    0.07
    è´¨çļĦ
    0.06
    á»Ńng
    0.06
    Activations Density 0.033%

    No Known Activations