© 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. 23160
    Prev
    Next
    INDEX
    Explanations

    selected medical conditions

    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
    itto
    -0.07
    è¿ijçļĦ
    -0.07
    usen
    -0.06
    _changed
    -0.06
     cann
    -0.06
    attle
    -0.06
    ISO
    -0.06
    _almost
    -0.06
    ><![
    -0.06
    ä¸įè¦ģå¿ĺäºĨ
    -0.06
    POSITIVE LOGITS
    listed
    0.09
     listed
    0.09
    æīĢåĪĹ
    0.08
    åĪĹ举
    0.08
    æ¸ħåįķ
    0.08
    _LIST
    0.08
    éĢIJä¸Ģ
    0.08
    åħ³
    0.07
     liá»ĩt
    0.07
    éĹľ
    0.07
    Activations Density 0.017%

    No Known Activations