© 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. 56692
    Prev
    Next
    INDEX
    Explanations

    equations and math problems

    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
     Mestre
    -0.08
    renc
    -0.07
    åĵī
    -0.07
    ä¸įè¾¾
    -0.07
    ancia
    -0.07
    ĶĦ
    -0.07
     sinyal
    -0.07
    fx
    -0.07
    #
    -0.07
    ØŃدث
    -0.07
    POSITIVE LOGITS
    æīĭ足
    0.08
    æĸ°ä¸Ģå±Ĭ
    0.07
    æ¯Ĥ
    0.07
    æľĢæĸ°çīĪ
    0.07
    elum
    0.07
    大åIJĮ
    0.06
    ulli
    0.06
    åī²
    0.06
    dens
    0.06
    лем
    0.06
    Activations Density 0.016%

    No Known Activations