© 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. 37766
    Prev
    Next
    INDEX
    Explanations

    Determine, compute, write

    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
    endet
    -0.08
    engar
    -0.07
    è·¯éĢı
    -0.07
    lopen
    -0.07
    lickr
    -0.07
    иво
    -0.07
    éĤ£ä¹Ī大
    -0.07
    dea
    -0.07
    å®ĥæĺ¯ä¸Ģ个
    -0.07
    iale
    -0.07
    POSITIVE LOGITS
     Yourself
    0.09
     yourself
    0.09
    lah
    0.09
    并
    0.08
    並
    0.08
    æĪijåIJ§
    0.07
    issez
    0.07
     пожалÑĥйÑģÑĤа
    0.07
     yourselves
    0.07
    并æıIJä¾Ľ
    0.07
    Activations Density 0.133%

    No Known Activations