© 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. 16527
    Prev
    Next
    INDEX
    Explanations

    example of content types

    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
    诸å¦Ĥ
    -0.09
    æĺ¯åIJ¦æľī
    -0.07
    åĽ¾çīĩæĪĸ
    -0.07
    æĺ¯åIJ¦åŃĺåľ¨
    -0.07
    æѤçķª
    -0.07
    èĶļ
    -0.07
    ")!=
    -0.07
    éĤ£ä¹Īå¤ļ
    -0.07
    å®ŀè´¨ä¸Ĭ
    -0.07
    AZY
    -0.07
    POSITIVE LOGITS
     typical
    0.08
     ways
    0.08
    æijĺèĩª
    0.08
    ä¾Ľå¤§å®¶åıĤèĢĥ
    0.08
    ä»ħä¾ĽåıĤèĢĥ
    0.08
    å°ıç¼ĸ为大家æķ´çIJĨçļĦ
    0.07
    ä¾Ľ
    0.07
    ä¾ĽæĤ¨
    0.07
    olen
    0.07
     outlines
    0.07
    Activations Density 0.668%

    No Known Activations