© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 58829
    Prev
    Next
    INDEX
    Explanations

    math identity element 1

    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§Ħå¾ĭ
    -0.08
    秽
    -0.08
    èĤ¾çĤİ
    -0.08
    masked
    -0.07
    åıĬéĻĦåĬł
    -0.07
    è§Ħå¾ĭçļĦ
    -0.07
    è¦ıå¾ĭ
    -0.07
    .Mask
    -0.07
    åѦæ³ķ
    -0.07
    aly
    -0.07
    POSITIVE LOGITS
    ikka
    0.08
    æ¯į
    0.07
     Wor
    0.07
    ringe
    0.07
    ilÃł
    0.07
    itora
    0.07
    ä¸įåľ¨
    0.07
    æĸ°ä¸ĸçķĮ
    0.07
    å¿ĥæĥ³äºĭæĪIJ
    0.07
    æĹ¥åIJij
    0.06
    Activations Density 0.003%

    No Known Activations