© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 2851
    Prev
    Next
    INDEX
    Explanations

    date and time stamps

    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
     Fisc
    -0.09
    Ñħан
    -0.09
    verity
    -0.08
    रà¥įड
    -0.08
    æijĺç¼ĸ
    -0.08
    ovn
    -0.08
    ä¸ĭåIJĮ
    -0.07
    mates
    -0.07
     appunto
    -0.07
    .gnu
    -0.07
    POSITIVE LOGITS
    æĪĸèĢħ缴æİ¥
    0.10
    æĪĸèĢħ
    0.10
    æĪĸ缴æİ¥
    0.10
    æĪĸèĢħ说
    0.09
    æĪĸèĢħæĺ¯
    0.09
    çŃīçŃī
    0.08
    æĪĸæĺ¯
    0.08
    æĪĸèĢħåħ¶ä»ĸ
    0.08
    ...
    0.08
     or
    0.08
    Activations Density 0.013%

    No Known Activations