© 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. 28612
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation/hyphens

    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
    çļĨæľī
    -0.07
    åĪĨ享èĩ³
    -0.07
    idia
    -0.07
    æĹ¥ä»¥æĿ¥
    -0.07
    edom
    -0.07
    æĺĵçĪĨ
    -0.07
     Tenn
    -0.07
    ighb
    -0.07
    èĬ±æŀľ
    -0.07
    FLAGS
    -0.06
    POSITIVE LOGITS
    ower
    0.08
    .ud
    0.07
    ban
    0.07
    threads
    0.07
    ba
    0.07
    arias
    0.07
    ewire
    0.07
    umb
    0.06
    走好
    0.06
    Äĥt
    0.06
    Activations Density 0.104%

    No Known Activations