© 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. 34009
    Prev
    Next
    INDEX
    Explanations

    prior art

    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
    è¿ĺä¼ļåĩºçİ°
    -0.08
    è¿ĻçŃī
    -0.07
     sogar
    -0.07
    éĻ¤æѤ
    -0.07
    使åħ¶
    -0.07
     otherwise
    -0.07
    auge
    -0.07
     remaining
    -0.07
    ç²¾ç¥ŀçļĦ
    -0.07
    使ä¹ĭ
    -0.06
    POSITIVE LOGITS
    ä¸ĢèĪ¬æĿ¥è¯´
    0.07
    åIJįæĢĿ
    0.07
    åĽ½å®¶åĴĮåľ°åĮº
    0.07
    _DECLARE
    0.07
    è´Łè´£å¯¹
    0.07
    éĹ®é¢ĺæĺ¯
    0.07
    åĪĽå»ºäºİ
    0.07
    ial
    0.07
    主è¦ģæĺ¯æĮĩ
    0.07
     기본ìłģìľ¼ë¡ľ
    0.07
    Activations Density 0.220%

    No Known Activations