© 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. 62322
    Prev
    Next
    INDEX
    Explanations

    shapes and their geometric forms

    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
    åī¯æľ¬
    -0.08
    è¿ľè¿ij
    -0.08
    ä¸Ģ对ä¸Ģ
    -0.08
    åı£å¤´
    -0.07
    çĪIJ
    -0.07
    åĮĸåIJį
    -0.07
    amba
    -0.07
    iad
    -0.06
     Permit
    -0.06
    æĪijåľ¨
    -0.06
    POSITIVE LOGITS
    è¿Ļéĥ¨åĪĨ
    0.10
     portion
    0.09
    éĥ¨åĪĨçļĦ
    0.09
    portion
    0.09
    å°ıéĥ¨åĪĨ
    0.08
    _INCLUDED
    0.08
    éĥ¨åĪĨæĺ¯
    0.08
    çļĦéĿ¢ç§¯
    0.08
    ä¸īéĥ¨åĪĨ
    0.08
    æĢ»éĿ¢ç§¯
    0.08
    Activations Density 0.013%

    No Known Activations