© 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. 585
    Prev
    Next
    INDEX
    Explanations

    numbers, units, and specific item types

    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
    å»·
    -0.10
    umur
    -0.07
    åıİçĽĬ
    -0.07
    gat
    -0.07
    ixel
    -0.07
    spacer
    -0.07
    æłħ
    -0.07
    éĽ·è¾¾
    -0.06
    oods
    -0.06
    ä¼łå¯¼
    -0.06
    POSITIVE LOGITS
    说æľī
    0.07
    æĢ»æķ°çļĦ
    0.07
    ovie
    0.07
    å½ĵæĻļ
    0.07
    çĬ¯
    0.07
    IllegalArgumentException
    0.07
    éĹ¹
    0.07
     Rit
    0.07
    istrib
    0.07
     pattern
    0.06
    Activations Density 0.001%

    No Known Activations