© 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. 15417
    Prev
    Next
    INDEX
    Explanations

    lysosomal

    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
    æĢģåĬ¿
    -0.08
    å¾Ĵ
    -0.08
    第ä¸Ģç¯ĩ
    -0.07
    æĿŀ
    -0.07
    curl
    -0.07
    æŀ¶è®¾
    -0.07
    angk
    -0.07
    ximity
    -0.07
    åĿĬ
    -0.07
     overd
    -0.07
    POSITIVE LOGITS
     recycling
    0.08
    éħ¸åĮĸ
    0.08
     contents
    0.08
     Acid
    0.08
    éģĵè¿ľ
    0.07
    ubil
    0.07
     merger
    0.07
     emptied
    0.07
     Contents
    0.07
    éĽ·é¸£
    0.07
    Activations Density 0.037%

    No Known Activations