© 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. 56289
    Prev
    Next
    INDEX
    Explanations

    integral convergence and limits

    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
    æĹ¥ä¹ħ
    -0.07
    å¦ĤæŀľæĬĬ
    -0.07
    æŃ¢æ°´
    -0.06
    åħ¼
    -0.06
    /write
    -0.06
    éĢIJ
    -0.06
    swire
    -0.06
    A
    -0.05
    annya
    -0.05
    æŃ¥åŃIJ
    -0.05
    POSITIVE LOGITS
    ãģıãĤĮãģŁ
    0.08
    inclusive
    0.08
    ç¥Ŀç¦ıä½ł
    0.07
    .utf
    0.07
    å°Ķå¾·
    0.07
    :request
    0.07
     UIL
    0.07
    olan
    0.07
    VAS
    0.07
     Bracket
    0.07
    Activations Density 0.002%

    No Known Activations