© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 42755
    Prev
    Next
    INDEX
    Explanations

    medical findings and abnormalities

    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
    ç¹ģ
    -0.08
    ç»ıæµİåĴĮ
    -0.07
     измелÑĮ
    -0.06
     Delicious
    -0.06
    åĴĮçݯå¢ĥ
    -0.06
    _ask
    -0.06
    讲æ±Ĥ
    -0.06
    eln
    -0.06
    alph
    -0.06
    å®ī
    -0.06
    POSITIVE LOGITS
    å½±åĥıåѦ
    0.10
     abnormalities
    0.10
     findings
    0.10
     detected
    0.10
     suggestive
    0.09
    æ£Ģåĩº
    0.09
     clinically
    0.09
    çīĩåŃIJ
    0.08
     Detected
    0.08
     âī¥
    0.08
    Activations Density 0.557%

    No Known Activations