© 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. 37643
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols

    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¸ĭä¸Ģ级
    -0.09
    alj
    -0.09
    éĢIJ级
    -0.09
    pany
    -0.08
    å±Ĥå±Ĥ
    -0.08
     grads
    -0.08
    ç©Ĩ
    -0.08
    æ´»
    -0.08
     Grad
    -0.07
    Grad
    -0.07
    POSITIVE LOGITS
    åīįåIJİ
    0.10
    ä¸ŃéĹ´
    0.10
    å·¦åı³
    0.09
    åīįå¾Į
    0.09
    ä¸Ńéĸĵ
    0.08
    éĹ´éļĶ
    0.08
     inters
    0.08
    ä¸ŃéĹ´çļĦ
    0.08
     sym
    0.07
     intermittent
    0.07
    Activations Density 0.037%

    No Known Activations