© 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. 38362
    Prev
    Next
    INDEX
    Explanations

    grammar, games, golf, lifeguard, voucher

    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
    êµī
    -0.08
    çļĦè¯Ŀé¢ĺ
    -0.08
     Mati
    -0.07
    .Topic
    -0.07
     Maver
    -0.07
    ë©ķ
    -0.07
    çijŀå®ī
    -0.07
    .Formatter
    -0.07
    çĶ¨ä¹¦
    -0.07
    æĹ¥çħ§
    -0.07
    POSITIVE LOGITS
    群
    0.06
    yeur
    0.06
    ApplicationBuilder
    0.06
    åĪ¥
    0.06
    GN
    0.06
    _memcpy
    0.06
    ington
    0.05
    elus
    0.05
    pcl
    0.05
    ä¸ĢèĪ¬çļĦ
    0.05
    Activations Density 1.978%

    No Known Activations