© 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. 11203
    Prev
    Next
    INDEX
    Explanations

    Helicobacter pylori and ulcers

    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
    天河
    -0.09
    æŀĿæĿ¡
    -0.09
    æĽ³
    -0.08
    è§Ĩç½ij
    -0.08
    å±ķ
    -0.07
    osu
    -0.07
    ä¸ĭè½½åľ°åĿĢ
    -0.07
     пеÑĢео
    -0.07
    äºĨçľ¼
    -0.07
    imah
    -0.07
    POSITIVE LOGITS
    å¹½éŨ
    0.12
    èĥĥ
    0.12
    åħ»èĥĥ
    0.12
     gastric
    0.11
    èĥĥæºĥçĸ¡
    0.11
    åįģäºĮæĮĩèĤł
    0.10
    èĥĥéħ¸
    0.10
     Gastr
    0.10
     gastr
    0.10
     gast
    0.10
    Activations Density 0.122%

    No Known Activations