© 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. 32792
    Prev
    Next
    INDEX
    Explanations

    adding or removing actions

    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
     Beckham
    -0.07
    nikov
    -0.07
    .txt
    -0.07
    à¸ĩ
    -0.06
    niki
    -0.06
    å¸ģ
    -0.06
    åıįåIJij
    -0.06
    Dir
    -0.06
    ambda
    -0.06
    åĪª
    -0.06
    POSITIVE LOGITS
    浩
    0.08
    æĸ°åŁİ
    0.07
     Raw
    0.07
    rale
    0.07
    ä¸ĢèĪ¬é¡¹çĽ®
    0.07
     raw
    0.07
    kep
    0.07
    说ä¸Ģåı¥
    0.06
    ç«Ńè¯ļ
    0.06
    Raw
    0.06
    Activations Density 0.016%

    No Known Activations