© 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. 25158
    Prev
    Next
    INDEX
    Explanations

    single, individual, discrete units

    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
    enner
    -0.08
    è¯Ħæ¯Ķ
    -0.07
    icont
    -0.07
    èĽĨ
    -0.07
    orat
    -0.07
    è¿Ŀæ³ķåĴĮä¸įèī¯ä¿¡æģ¯ä¸¾æĬ¥
    -0.07
    å±±é«ĺ
    -0.07
     Gew
    -0.07
    èķ
    -0.07
    ä¸Ģå¼ı
    -0.07
    POSITIVE LOGITS
     discrete
    0.12
    åįķ个
    0.10
    éļıæľº
    0.10
     individual
    0.10
    /single
    0.10
     single
    0.10
     singolo
    0.09
    åįķ次
    0.09
    个ä½ĵ
    0.09
     indiv
    0.09
    Activations Density 0.024%

    No Known Activations