© 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. 17377
    Prev
    Next
    INDEX
    Explanations

    saucepan

    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
    à¸Īัà¸ĩ
    -0.07
    ä¿Ŀå¯Ĩ
    -0.07
     bersangkutan
    -0.07
    hoff
    -0.07
     Confidential
    -0.06
    ixon
    -0.06
     redistributed
    -0.06
    eldo
    -0.06
    èģĺ
    -0.06
    asured
    -0.06
    POSITIVE LOGITS
    åı¦ä¸Ģè¾¹
    0.08
    çŃīåħ¶ä»ĸ
    0.08
    æĪijä¹Łè¦ģ
    0.08
    åIJĮçIJĨ
    0.07
    åIJĮæł·
    0.07
     ÑĤоже
    0.07
    åı¦ä¸ĢåįĬ
    0.07
     likewise
    0.07
     similarly
    0.07
     ebenfalls
    0.07
    Activations Density 0.014%

    No Known Activations