© 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. 44169
    Prev
    Next
    INDEX
    Explanations

    maximal number

    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
    ìĸ´ëĤĺ
    -0.08
    走好
    -0.07
    åIJīå°Ķ
    -0.07
    azos
    -0.07
    Äįas
    -0.07
    abord
    -0.07
    æĹłè®ºä»İ
    -0.07
    stry
    -0.07
    }):
    -0.07
    ç»´å¥ĩ
    -0.07
    POSITIVE LOGITS
    èĭ¥æľī
    0.07
     subsequently
    0.07
    æĺ¯åIJ¦åŃĺåľ¨
    0.07
    ä¸Ģåħ±æľī
    0.07
     consequently
    0.07
     alternatively
    0.06
     sesungguhnya
    0.06
     ’
    0.06
    chie
    0.06
    å¦Ĥæŀľæľī
    0.06
    Activations Density 0.025%

    No Known Activations