© 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. 983
    Prev
    Next
    INDEX
    Explanations

    defecation, swallowing, movements

    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
    æ¼Ĥ
    -0.09
     sold
    -0.07
    .rm
    -0.07
    éĤĤéĢħ
    -0.07
    åłķ
    -0.07
    èIJį
    -0.06
    imon
    -0.06
    ẻ
    -0.06
    åĵŃ声
    -0.06
     ëģĮ
    -0.06
    POSITIVE LOGITS
    vain
    0.10
    çĶ¨åĬĽ
    0.09
     vain
    0.09
     forcefully
    0.08
     пÑĢилага
    0.08
    æĨĭ
    0.08
     unsuccessfully
    0.08
     عض
    0.08
     ìŀIJìĦ¸
    0.08
     cá»Ń
    0.07
    Activations Density 0.045%

    No Known Activations