© 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. 11363
    Prev
    Next
    INDEX
    Explanations

    academic references and citations

    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
    ãĥ¥ãĥ¼
    -0.07
    usch
    -0.07
    åĭĴ
    -0.07
    WG
    -0.07
    ikian
    -0.07
    管çIJĨæīĢ
    -0.07
    绣
    -0.06
    ÎŃν
    -0.06
    ulen
    -0.06
    tran
    -0.06
    POSITIVE LOGITS
    èıģ
    0.07
    ÐĶÐIJÐł
    0.07
    æĹ¥æ¶Īæģ¯
    0.07
    .vue
    0.07
    ace
    0.07
    临
    0.07
    é½IJé½IJ
    0.07
    åĴĮ交æµģ
    0.07
    åªĴ
    0.07
    ifen
    0.07
    Activations Density 0.166%

    No Known Activations