© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 52025
    Prev
    Next
    INDEX
    Explanations

    simple, simplistic, simple form

    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
    Negative Logits
    ä¸įä»ħæľī
    -0.07
    ä¸įä»ħä»ħæĺ¯
    -0.07
    awe
    -0.07
    ä¸įåıªæĺ¯
    -0.06
    请åĬł
    -0.06
    ä¸įåįķ
    -0.06
     nuanced
    -0.06
     Klim
    -0.06
    çļĦ缸åħ³
    -0.06
     ê¶ģ
    -0.06
    POSITIVE LOGITS
     simplicity
    0.16
    ç®ĢåįķçļĦ
    0.15
    ç®Ģåįķ
    0.15
    /simple
    0.14
     simpler
    0.14
     simple
    0.14
    Simple
    0.14
    ç®ĢåĮĸ
    0.13
    ç®Ģæĺĵ
    0.13
    ç»ĵæŀĦç®Ģåįķ
    0.13
    Activations Density 0.181%

    No Known Activations