© 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. 37859
    Prev
    Next
    INDEX
    Explanations

    math and induced representations

    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
    ÙĪÙĥ
    -0.08
    ibe
    -0.07
    wg
    -0.06
    olat
    -0.06
    dead
    -0.06
     Cabe
    -0.06
     Ok
    -0.06
    bod
    -0.06
    пл
    -0.06
     Pian
    -0.06
    POSITIVE LOGITS
    举äºļ
    0.08
     universale
    0.08
     manc
    0.08
    iteli
    0.07
    ¤íĮ
    0.07
     intime
    0.07
     بعدÙĩ
    0.07
    åĨįæĢİä¹Ī
    0.07
    æĪĸåĪłéĻ¤
    0.07
    haar
    0.07
    Activations Density 0.027%

    No Known Activations