© 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. 1423
    Prev
    Next
    INDEX
    Explanations

    enables traffic

    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
     thereof
    -0.11
     accordingly
    -0.10
    使ä¹ĭ
    -0.10
    åı¯æĥ³èĢĮçŁ¥
    -0.09
    åį´æ²¡
    -0.09
    ä¹Łä¸įä¾ĭå¤ĸ
    -0.08
     daÃŃ
    -0.08
    SetText
    -0.08
    éļıä¹ĭ
    -0.07
    åıĤä¸İåħ¶ä¸Ń
    -0.07
    POSITIVE LOGITS
    并ä¸įæĺ¯
    0.09
     ONLY
    0.09
    并éĿŀ
    0.08
    ä¸įä»ħä»ħ
    0.08
    并ä¸į代表
    0.08
    并ä¸į
    0.08
    并ä¸įä¼ļ
    0.08
    并ä¸įéľĢè¦ģ
    0.08
    并ä¸įæĦıåij³çĿĢ
    0.08
    éĿŀ常容æĺĵ
    0.08
    Activations Density 0.275%

    No Known Activations