© 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. 54965
    Prev
    Next
    INDEX
    Explanations

    comparatively greater

    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¸į计
    -0.08
    æŀģæľīåı¯èĥ½
    -0.08
     overwhelming
    -0.07
    anga
    -0.07
    å®Įåħ¨
    -0.07
    ignano
    -0.07
    æŀģ端
    -0.07
    abay
    -0.07
    æŀģ
    -0.07
    araf
    -0.06
    POSITIVE LOGITS
     moderately
    0.13
     comparatively
    0.12
    éĢĬèī²
    0.12
    ä¸įå¦Ĥ
    0.12
    æ¯Ķä¸įä¸Ĭ
    0.12
     moderate
    0.11
    çĽ¸å¯¹è¾ĥä½İ
    0.11
     modest
    0.11
    ä¸įåıĬ
    0.11
    èĻ½æľī
    0.10
    Activations Density 0.135%

    No Known Activations