© 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. 1180
    Prev
    Next
    INDEX
    Explanations

    medical or technical 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
    rer
    -0.08
    nard
    -0.08
    orz
    -0.08
    çŃīåĪ°äºĨ
    -0.08
    æľ¬åľºæ¯ĶèµĽ
    -0.08
    cmds
    -0.08
    åİŁåĽłå°±æĺ¯
    -0.08
    rails
    -0.08
    çļĦéĺ³åħī
    -0.08
    ore
    -0.07
    POSITIVE LOGITS
    以æѤæĿ¥
    0.06
    åIJĮä¸ļ
    0.06
    åIJ«ä¹ī
    0.06
    å¥½äºĽ
    0.06
    åĪĨåĢ¼
    0.06
    æ¤Ĵ
    0.06
    ley
    0.06
    åIJ¬èµ·æĿ¥
    0.06
    аÑĢа
    0.06
    èĶ½
    0.06
    Activations Density 0.061%

    No Known Activations