© 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. 8360
    Prev
    Next
    INDEX
    Explanations

    includes an

    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¸įèĩ³äºİ
    -0.07
     Intermediate
    -0.07
    stin
    -0.07
     hell
    -0.07
    ipmap
    -0.06
    Intermediate
    -0.06
    ëĭ¥
    -0.06
    .mixin
    -0.06
    æīĢ欲
    -0.06
     Vest
    -0.06
    POSITIVE LOGITS
    ä¸įä»ħæľī
    0.11
     normal
    0.10
    æŃ£å¸¸
    0.10
    éĻ¤äºĨæľī
    0.10
    éĻ¤äºĨ
    0.10
    æŃ£å¸¸çļĦ
    0.10
    éĻ¤äºĨåľ¨
    0.10
    éĻ¤äºĨè¦ģ
    0.09
    ä¸įä»ħ
    0.09
     помимо
    0.09
    Activations Density 0.386%

    No Known Activations