© 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. 55181
    Prev
    Next
    INDEX
    Explanations

    former teacher, journalist, businessman

    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
     Unless
    -0.09
     unless
    -0.09
     Monteiro
    -0.08
    unless
    -0.07
    éĻ¤éĿŀ
    -0.07
    Unless
    -0.07
    tober
    -0.07
    æ¸ĵ
    -0.07
    åıªè¦ģæĪij们
    -0.07
    éļĶ
    -0.07
    POSITIVE LOGITS
     stint
    0.12
    มาà¸ģà¹Īà¸Ńà¸Ļ
    0.12
    çļĦç»ıåİĨ
    0.10
    æľŁéĹ´
    0.09
    åħĪåIJİåľ¨
    0.09
    -turned
    0.09
    ãĤĴçµĮãģ¦
    0.09
    æľŁéĹ´çļĦ
    0.09
    æľŁéĸĵ
    0.09
    积累äºĨ丰å¯ĮçļĦ
    0.09
    Activations Density 0.972%

    No Known Activations