© 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. 19526
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions or questions

    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
    Leaks
    -0.07
    è¿ijä¹İ
    -0.07
    )>>
    -0.07
    æĺ¾å¾ĹæľīäºĽ
    -0.07
    /ss
    -0.07
    对æķ´ä¸ª
    -0.07
    ä¸ĬèµĽåŃ£
    -0.07
    [at
    -0.06
    åĬ¨åĬĽçļĦ
    -0.06
    æĹłæĦı
    -0.06
    POSITIVE LOGITS
    ()._
    0.06
    æľ¬é¢ĺ解éĩĬ
    0.06
    ·
    0.06
    æľ¬é¢ĺèĢĥæŁ¥
    0.06
     Ans
    0.06
     gunman
    0.06
    <img
    0.06
    å±ħæĺĵ
    0.06
    åİŁä»·
    0.06
    æĺİæĺİ
    0.06
    Activations Density 0.037%

    No Known Activations