© 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. 34917
    Prev
    Next
    INDEX
    Explanations

    example, details, facts, background, guess

    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
    abd
    -0.08
    eways
    -0.07
    cce
    -0.07
     newList
    -0.07
    erti
    -0.07
    chetti
    -0.07
    ä½ıçĿĢ
    -0.07
    cim
    -0.07
     estou
    -0.07
    ajer
    -0.07
    POSITIVE LOGITS
    è¶Ĭæĥ³
    0.07
     Disk
    0.07
    客æĪ·è¦ģæ±Ĥ
    0.07
     typical
    0.07
    åIJIJ
    0.07
    éļĶå£ģ
    0.07
     disk
    0.07
    _disk
    0.07
    disk
    0.06
    yan
    0.06
    Activations Density 0.011%

    No Known Activations