© 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. 43799
    Prev
    Next
    INDEX
    Explanations

    finite boundary conditions

    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
    ä¸İæĻ®éĢļ
    -0.08
    -opacity
    -0.07
    ä¿Ŀåģ¥
    -0.07
     derail
    -0.07
     cha
    -0.06
    éļı身
    -0.06
    .hover
    -0.06
    äºĭä¸Ń
    -0.06
    åĴĮæĻ®éĢļ
    -0.06
    åħĪ导
    -0.06
    POSITIVE LOGITS
     finite
    0.12
    Finite
    0.11
    finite
    0.11
     Finite
    0.10
    æľīéĻIJ
    0.09
     symmetry
    0.08
    åĽĽåij¨
    0.08
    è¾¹çķĮ
    0.08
    æĺ¯æľīéĻIJçļĦ
    0.08
    Setup
    0.08
    Activations Density 0.015%

    No Known Activations