© 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. 13181
    Prev
    Next
    INDEX
    Explanations

    related to results or output

    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
    angani
    -0.07
    å¤ĸæĸĩ
    -0.07
    ণ
    -0.07
    ÙĪض
    -0.06
    åĪ°æľĢåIJİ
    -0.06
    ç»Ī审
    -0.06
    æĸĹ
    -0.06
    gaard
    -0.06
     ÑģÑĤаÑĢÑĪе
    -0.06
    æĽ´æĸ°æĹ¥æľŁ
    -0.06
    POSITIVE LOGITS
    aines
    0.07
    ergic
    0.07
    otrop
    0.07
    ä¿ĿæĬ¤çݯå¢ĥ
    0.07
    lee
    0.07
    edList
    0.07
    å·²æĪIJ
    0.07
    еÑĢж
    0.07
    اÙĩ
    0.07
    ails
    0.06
    Activations Density 0.049%

    No Known Activations