© 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. 35031
    Prev
    Next
    INDEX
    Explanations

    initials and names

    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
    Negative Logits
    browse
    -0.07
    nitz
    -0.07
    æĹ¥è¢«
    -0.07
    landa
    -0.07
    hoek
    -0.07
    æĭĸçĿĢ
    -0.07
    unami
    -0.07
    ë°ĶìĿ´
    -0.07
    atot
    -0.07
    yam
    -0.07
    POSITIVE LOGITS
     et
    0.08
    rys
    0.07
     &
    0.07
    å¿ĺè®°å¯Ĩçłģ
    0.06
    esty
    0.06
     rac
    0.06
    éĹ½
    0.06
    оÑģÑĤа
    0.06
     R
    0.06
    alse
    0.06
    Activations Density 0.013%

    No Known Activations