© 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. 49537
    Prev
    Next
    INDEX
    Explanations

    lists, definitions, and titles

    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
    undler
    -0.07
    é¼ĵ
    -0.07
    rie
    -0.06
    èģª
    -0.06
    .addTo
    -0.06
    麻辣
    -0.06
    zik
    -0.06
    å¸ĥæĭī
    -0.06
    eson
    -0.06
    uster
    -0.06
    POSITIVE LOGITS
     Gim
    0.08
    onaut
    0.08
    ä¸įçŁ¥éģĵèĩªå·±
    0.08
    ieta
    0.07
    ForKey
    0.07
    %@
    0.07
    空ä¸ŃçļĦ
    0.07
     antlr
    0.07
    onha
    0.07
    ÃŃv
    0.07
    Activations Density 0.025%

    No Known Activations