© 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. 62486
    Prev
    Next
    INDEX
    Explanations

    is derived, varies, closest, disclosed, conjunction

    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
     ÑģколÑĮ
    -0.07
    idler
    -0.06
     infinitely
    -0.06
    æŃ£æĺ¯
    -0.06
    被è§Ĩ为
    -0.06
    è¿ĺæľīå¾Īå¤ļ
    -0.06
    èques
    -0.06
     ái
    -0.06
    æ·±æĥħ
    -0.06
    åľ¨æĹ¥å¸¸
    -0.06
    POSITIVE LOGITS
     Tend
    0.09
    åı¯èĥ½ä¸İ
    0.09
     likely
    0.09
    æĪĸ许æľī
    0.08
    åIJ¬èµ·æĿ¥
    0.08
    Lik
    0.08
    andia
    0.08
     Likely
    0.08
    ommel
    0.08
     reportedly
    0.07
    Activations Density 0.008%

    No Known Activations