© 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. 24439
    Prev
    Next
    INDEX
    Explanations

    biological and medical terms

    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
    ATER
    -0.08
    å¤ļæĸ¹
    -0.07
    ĭ
    -0.07
    å¤ļæĸ¹éĿ¢
    -0.07
    allis
    -0.07
    éĢIJä¸Ģ
    -0.07
    aldas
    -0.06
    å¤ļå¤Ħ
    -0.06
    åIJĦæĸ¹
    -0.06
    礼
    -0.06
    POSITIVE LOGITS
    è¿Ļ两ç§į
    0.11
    è¿Ļ两个
    0.10
    éĢĻåħ©åĢĭ
    0.09
    éĢĻåħ©
    0.08
    è¿Ļ两ä½į
    0.08
    ä½ľå¥½
    0.08
    è¿Ļ两
    0.08
    è¿Ļä¸īç§į
    0.08
    åĪĨåĪ«ä¸º
    0.08
    imis
    0.08
    Activations Density 0.293%

    No Known Activations