© 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. 21446
    Prev
    Next
    INDEX
    Explanations

    medical risk

    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
    iria
    -0.06
    æĺ¯æł¹æį®
    -0.06
    æīĢæľī人
    -0.06
    æ³ķ人
    -0.06
    thon
    -0.06
    باد
    -0.06
    usti
    -0.06
    è¾Ľéħ¸
    -0.06
    ideon
    -0.06
    ä¹ĭåħī
    -0.05
    POSITIVE LOGITS
    è¿Ļç§įæĥħåĨµ
    0.12
    该æĢİä¹ĪåĬŀ
    0.10
    è¿Ļç§įæĥħåĨµä¸ĭ
    0.09
    è¿Ļæł·çļĦæĥħåĨµ
    0.09
    æĢİä¹ĪåĬŀ
    0.09
    çŃīæĥħåĨµ
    0.08
     sekalipun
    0.08
    iggio
    0.08
    éĹ®é¢ĺæŶ
    0.08
    maal
    0.08
    Activations Density 0.073%

    No Known Activations