© 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. 65096
    Prev
    Next
    INDEX
    Explanations

    onchocerciasis, Coccidioides, diabetes, trichomonas

    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
    ossa
    -0.06
    ("[%
    -0.06
    èque
    -0.06
     slew
    -0.06
    ê¸ī
    -0.06
    obia
    -0.06
    enders
    -0.06
    owan
    -0.06
     gara
    -0.06
    à¸Īร
    -0.06
    POSITIVE LOGITS
    bart
    0.08
    ÏĢαν
    0.08
    太éĥİ
    0.07
    ην
    0.07
    çŃīé¢Ĩ导
    0.07
    uy
    0.07
    asm
    0.07
    ]+)/
    0.07
    ÂŃing
    0.07
    .ly
    0.07
    Activations Density 0.096%

    No Known Activations