© 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. 19917
    Prev
    Next
    INDEX
    Explanations

    closest, highest, fastest

    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
    ango
    -0.08
    ä¸įè¿Ľ
    -0.08
    à¸Ĺัà¹īà¸ĩสิà¹īà¸Ļ
    -0.07
    ä¸įåħ¥
    -0.07
    [href
    -0.07
    iani
    -0.07
    rove
    -0.07
    Living
    -0.07
     concernés
    -0.07
    åħ¸åŀĭ
    -0.07
    POSITIVE LOGITS
     наим
    0.12
    æľĢéĢĤåIJĪ
    0.11
     closest
    0.11
    æľĢèĥ½
    0.11
     fastest
    0.10
    closest
    0.10
     наиболÑĮ
    0.10
     highest
    0.10
     наиболее
    0.10
    è§Ħ模æľĢ大
    0.10
    Activations Density 0.054%

    No Known Activations