© 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. 34725
    Prev
    Next
    INDEX
    Explanations

    seizing pulmonary artery vein

    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
     uff
    -0.07
    uffed
    -0.07
    çݰ代åĮĸ建设
    -0.07
    anes
    -0.07
    etz
    -0.07
    Æ°
    -0.07
    zig
    -0.07
    赶ä¸Ĭ
    -0.07
    anan
    -0.06
     Bret
    -0.06
    POSITIVE LOGITS
    åľ°çĽĺ
    0.08
    veh
    0.07
    ær
    0.07
     seizing
    0.06
    ãĤ³ãĥł
    0.06
    WER
    0.06
    åĶ§
    0.06
    ä¸įåłª
    0.06
    å®īå¹³
    0.06
    uppen
    0.06
    Activations Density 1.896%

    No Known Activations