© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 39417
    Prev
    Next
    INDEX
    Explanations

    medical treatments and outcomes

    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
    æħ¢
    -0.07
     intu
    -0.07
    sdale
    -0.07
     Semen
    -0.07
    боÑĤ
    -0.07
    åįĹåĽ½
    -0.06
    èݱçī¹
    -0.06
    ĥĿ
    -0.06
    ↵      ↵
    -0.06
    Úĺ
    -0.06
    POSITIVE LOGITS
    æ¢Ń
    0.09
    并æľĢç»Ī
    0.08
    并èĥ½
    0.08
     profitable
    0.08
    éĵģé¾Ļ
    0.07
    åĴĮä½ľçĶ¨
    0.07
    并èİ·å¾Ĺ
    0.07
    并åıĸå¾Ĺ
    0.07
    åĴĮéĹ®é¢ĺ
    0.07
    —and
    0.07
    Activations Density 0.808%

    No Known Activations