© 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. 44559
    Prev
    Next
    INDEX
    Explanations

    shrink, incumbent, that, B, and, Junior, goals, from, Wednesday, Penn

    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
    unes
    -0.06
    Lookup
    -0.06
    éĥİ
    -0.06
    lish
    -0.06
    !(
    -0.06
    åĢ¡å¯¼
    -0.06
    -lang
    -0.06
    åĨħå¤ĸ
    -0.06
    æ´»äºĨ
    -0.06
     greens
    -0.06
    POSITIVE LOGITS
    صب
    0.08
    rys
    0.08
    aticon
    0.07
    ruÄį
    0.07
    à§į
    0.07
    sic
    0.07
    ×IJ×Ļ
    0.07
    Äģti
    0.07
    ÏĥÏĦι
    0.07
    awesome
    0.07
    Activations Density 0.061%

    No Known Activations