© 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. 52116
    Prev
    Next
    INDEX
    Explanations

    thermal followed by words like Wind, history, transfer, printer, function

    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
    lijk
    -0.08
    lijke
    -0.08
    Ø©
    -0.08
    ़
    -0.07
    ì§ĵ
    -0.07
    ej
    -0.07
    ÑģÑĤва
    -0.07
    возмо
    -0.07
    é¢ĺæĦı
    -0.07
     ÑĤаки
    -0.07
    POSITIVE LOGITS
    inks
    0.10
    ization
    0.10
    æĢ§çļĦ
    0.09
    ìĩł
    0.09
    ilogy
    0.09
    isation
    0.09
    isasi
    0.08
    alte
    0.08
    indsay
    0.08
    licity
    0.08
    Activations Density 0.025%

    No Known Activations