© 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. 65058
    Prev
    Next
    INDEX
    Explanations

    news reports and media mentions

    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
    amil
    -0.08
    ejs
    -0.08
    ä»Ģ麽
    -0.08
    å¼ķãģįç¶ļãģį
    -0.08
    amen
    -0.08
    èİİ士
    -0.07
    åľ¨æĢĿæĥ³ä¸Ĭ
    -0.07
     '.',
    -0.07
    æĿĤå¿Ĺ社
    -0.07
    åįĥåįĥä¸ĩ
    -0.07
    POSITIVE LOGITS
    Âł
    0.09
     notoriously
    0.08
     übrigens
    0.08
     recently
    0.07
    æľĢè¿ij
    0.07
    recent
    0.07
     famously
    0.07
     (
    0.07
    <a
    0.07
     recent
    0.06
    Activations Density 1.121%

    No Known Activations