© 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. 587
    Prev
    Next
    INDEX
    Explanations

    web content type and links

    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
    yson
    -0.08
    家æĶ¿
    -0.07
    ihal
    -0.07
    gable
    -0.07
    示
    -0.07
    åįĬ天
    -0.07
    tä
    -0.07
    bian
    -0.07
    alih
    -0.07
     Tong
    -0.07
    POSITIVE LOGITS
    usc
    0.06
    ä¹İåħ¶
    0.06
    orp
    0.06
    árd
    0.06
    ä¸Ģ寸
    0.06
    ç½ĹæĽ¼
    0.06
    à¸ģลาà¸ĩ
    0.06
    urz
    0.06
     forever
    0.06
    ONI
    0.06
    Activations Density 1.296%

    No Known Activations