© 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. 59968
    Prev
    Next
    INDEX
    Explanations

    recurrence relation, differential equations, coefficient bounds

    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
    iom
    -0.07
    oard
    -0.07
    _gb
    -0.07
    openid
    -0.07
    å¿ł
    -0.07
    acula
    -0.07
    å·«
    -0.07
    alap
    -0.07
    åijķ
    -0.07
    ño
    -0.07
    POSITIVE LOGITS
    为å®ĺ
    0.07
    ún
    0.07
    è¡ĹçļĦ
    0.07
    èµ·å§ĭ
    0.07
     starting
    0.07
    jet
    0.07
     odd
    0.07
    çŃ¹
    0.07
    fis
    0.07
     Pa
    0.06
    Activations Density 0.002%

    No Known Activations