© 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. 47107
    Prev
    Next
    INDEX
    Explanations

    disease conditions or environmental exposures

    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
     jad
    -0.08
     tơ
    -0.07
     cio
    -0.07
    Äĩi
    -0.07
    \/\/
    -0.07
    enser
    -0.06
    cia
    -0.06
    åºĶæīĭ
    -0.06
    edom
    -0.06
    atsu
    -0.06
    POSITIVE LOGITS
    çī¹åĪ«æĺ¯
    0.17
    å°¤åħ¶æĺ¯
    0.15
    主è¦ģæĺ¯
    0.15
    主è¦ģ为
    0.14
    主è¦ģæĺ¯æĮĩ
    0.14
    çī¹åĪ¥æĺ¯
    0.13
    éĢļ常æĺ¯
    0.13
     mainly
    0.13
    éĢļ常为
    0.13
     primarily
    0.13
    Activations Density 0.663%

    No Known Activations