© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 25394
    Prev
    Next
    INDEX
    Explanations

    RNA and genes

    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
    Not in Any Lists

    No Comments

    Negative Logits
    顺åħ¶èĩªçĦ¶
    -0.08
    æĸĩåįİ
    -0.08
    reck
    -0.07
    peater
    -0.07
    åijķ
    -0.07
    æ°´åľŁ
    -0.07
     Ordn
    -0.07
    迹
    -0.07
    lict
    -0.07
    æµģ线
    -0.07
    POSITIVE LOGITS
     shuttle
    0.09
    éī´å®ļ
    0.08
     ATP
    0.07
    /select
    0.07
     specificity
    0.07
     specialized
    0.07
    æµ·è§Ĵ
    0.07
    鸦
    0.07
     RNA
    0.07
    ç©¿æ¢Ń
    0.07
    Activations Density 0.009%

    No Known Activations