© 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. 4707
    Prev
    Next
    INDEX
    Explanations

    page numbers

    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
    _ASCII
    -0.08
    strup
    -0.08
    uckle
    -0.08
    ekar
    -0.08
    åįģåĽĽç«ł
    -0.08
    alon
    -0.07
    stag
    -0.07
    cini
    -0.07
    åĨĽåľ¨
    -0.07
    Äħtek
    -0.07
    POSITIVE LOGITS
    ikt
    0.07
    ug
    0.06
    åĢij
    0.06
    éĴ¦
    0.06
    çŃ¾
    0.06
    ÑĪиÑĤ
    0.06
     equ
    0.06
    çī¹æĸ¯
    0.06
    们çļĦ
    0.06
    ØŃات
    0.06
    Activations Density 0.017%

    No Known Activations