© 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. 58804
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and variables

    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
    äºİäºĭ
    -0.09
    ibat
    -0.08
    itel
    -0.08
    rop
    -0.08
    à°¦à±ģ
    -0.08
    cloak
    -0.07
    தி
    -0.07
    grave
    -0.07
    å¦Ĥçģ«å¦Ĥèį¼
    -0.07
    âĤ¬,
    -0.07
    POSITIVE LOGITS
    æĹ¢
    0.07
    mps
    0.07
    没æĶ¶
    0.06
    èīº
    0.06
    arg
    0.06
    ä»ĬæľĿ
    0.06
    å¤ķ
    0.06
    缴æİ¥æĪĸéĹ´æİ¥
    0.06
     tát
    0.06
    еÑħа
    0.06
    Activations Density 0.075%

    No Known Activations