© 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. 2497
    Prev
    Next
    INDEX
    Explanations

    chemical and biological tests

    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
    ooks
    -0.08
    è±¹
    -0.07
    建模
    -0.07
     harvested
    -0.07
     Pej
    -0.07
    ç¼ĿåIJĪ
    -0.06
    æĺİçıł
    -0.06
    æķ´å½¢ç¾İ容
    -0.06
    PFN
    -0.06
    ollower
    -0.06
    POSITIVE LOGITS
     tests
    0.13
    æµĭè¯ķ
    0.13
    éī´åĪ«
    0.12
    æ£ĢéªĮ
    0.12
    æ£Ģæµĭ
    0.12
     Tests
    0.12
     test
    0.12
     testing
    0.11
    éī´å®ļ
    0.11
     tester
    0.11
    Activations Density 0.062%

    No Known Activations