© 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. 46056
    Prev
    Next
    INDEX
    Explanations

    explaining or providing information

    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
    ä¸İä¹ĭ
    -0.10
     latter
    -0.08
     thereof
    -0.08
    åIJijåħ¶
    -0.07
    ä»ħæѤ
    -0.07
    atem
    -0.07
    该å±Ģ
    -0.07
    æľīæѤ
    -0.07
    ç»Ļä»ĸ们
    -0.07
    åIJİèĢħ
    -0.06
    POSITIVE LOGITS
    enius
    0.07
    é©
    0.07
    ä¸įä»ħæľī
    0.07
     Prós
    0.07
    å¸ĮæľĽåı¯ä»¥å¸®åĬ©
    0.07
    pun
    0.07
    inique
    0.07
    å°½åľ¨
    0.06
    è¶Ĭå¤ļ
    0.06
    æĺ¯çݰ代
    0.06
    Activations Density 0.558%

    No Known Activations