© 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. 52043
    Prev
    Next
    INDEX
    Explanations

    logic programming or expressions

    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
    sWith
    -0.14
    ами
    -0.10
    ing
    -0.09
    sst
    -0.09
    aub
    -0.09
    iÄį
    -0.09
    à¥Ģ
    -0.08
    aÄĩ
    -0.08
    à¥Ģल
    -0.08
    kommen
    -0.08
    POSITIVE LOGITS
    ìį¨
    0.11
    à¸ģาร
    0.08
    न
    0.08
    ously
    0.08
    ção
    0.08
    á»ĩn
    0.07
    umentos
    0.07
    ilee
    0.07
    forte
    0.07
    доз
    0.07
    Activations Density 0.019%

    No Known Activations