© 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. 10469
    Prev
    Next
    INDEX
    Explanations

    mathematical eta function

    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
    åIJĴ
    -0.09
    使åĩº
    -0.08
    timi
    -0.08
    ILER
    -0.08
    walt
    -0.08
    åľ¨åħ¨çľģ
    -0.08
    åĪ©çī©
    -0.08
    åı¯æ¢¦
    -0.08
    Ø´ÙĬØ©
    -0.08
     DRIVER
    -0.08
    POSITIVE LOGITS
     Eins
    0.07
    çIJī
    0.06
     hot
    0.06
    anne
    0.06
     Casc
    0.06
     Gran
    0.06
     Hot
    0.06
    imir
    0.06
    å¥ĩ
    0.06
    å£
    0.06
    Activations Density 0.002%

    No Known Activations