© 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. 671
    Prev
    Next
    INDEX
    Explanations

    mathematics or code logic

    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
     Tre
    -0.07
    elson
    -0.07
    åŃĺåľ¨çļĦ
    -0.07
     efficiencies
    -0.07
    è¿ijçļĦ
    -0.06
    ä¸įåĪ°çļĦ
    -0.06
    ehn
    -0.06
    åħ¨ä½ĵåħļåijĺ
    -0.06
    åģ¥åħ¨
    -0.06
    omal
    -0.06
    POSITIVE LOGITS
     denominator
    0.08
     modulo
    0.08
     numerator
    0.07
    ermen
    0.07
    ulto
    0.07
    opa
    0.07
    第ä¸Ģ项
    0.07
    ultos
    0.07
    eggio
    0.07
    nish
    0.07
    Activations Density 0.006%

    No Known Activations