© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 17397
    Prev
    Next
    INDEX
    Explanations

    unexpected or surprising renderings

    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
    arkin
    -0.08
    imps
    -0.08
    å·£
    -0.07
    å¸Ŀéĥ½
    -0.07
    .snp
    -0.07
    kers
    -0.07
    ignano
    -0.07
     cleanly
    -0.07
    ä¸Ģå¸Ĩ
    -0.07
    大好
    -0.07
    POSITIVE LOGITS
     unexpected
    0.12
    ä¸į该
    0.11
     unexpectedly
    0.11
     surprising
    0.10
    æĦıæĥ³ä¸įåĪ°çļĦ
    0.10
    é¢Ŀå¤ĸ
    0.10
    é¢Ŀå¤ĸçļĦ
    0.10
    æīĵçł´äºĨ
    0.10
     beyond
    0.09
     Unexpected
    0.09
    Activations Density 0.245%

    No Known Activations