© 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. 13044
    Prev
    Next
    INDEX
    Explanations

    is a question

    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
    cius
    -0.08
    à¸ĸ
    -0.07
    §
    -0.07
    abad
    -0.07
    è§Ģ
    -0.07
    åıªæĺ¯ä¸ºäºĨ
    -0.06
    ä¹ĭä¸Ĭ
    -0.06
    okal
    -0.06
    ika
    -0.06
    è§Ĥ
    -0.06
    POSITIVE LOGITS
     Ðĺменно
    0.10
     inilah
    0.10
    æŃ£æĺ¯åľ¨
    0.09
     appunto
    0.09
    æīįæĺ¯
    0.09
     itulah
    0.09
    æŃ£æĺ¯
    0.09
     именно
    0.09
    å°±æĺ¯è¿Ļæł·
    0.08
    illo
    0.08
    Activations Density 0.026%

    No Known Activations