© 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. 41840
    Prev
    Next
    INDEX
    Explanations

    computing purposes

    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
    åħ¶æīĢ
    -0.09
    porte
    -0.07
    loe
    -0.07
    æĽ´ç¬¦åIJĪ
    -0.07
    交åĬŀçļĦ
    -0.07
    å®ĥæīĢ
    -0.06
    èİ·å¥ĸåIJįåįķ
    -0.06
    çİĦå¾·
    -0.06
    欢快
    -0.06
     agenda
    -0.06
    POSITIVE LOGITS
    ãģĤãģı
    0.08
     purposes
    0.07
     przecież
    0.07
    æĪij们æŃ£åľ¨
    0.07
    缮çļĦå°±æĺ¯
    0.07
    owski
    0.07
    è°ģä¼ļ
    0.07
    actoring
    0.07
    çł°
    0.07
     purpose
    0.06
    Activations Density 0.038%

    No Known Activations