© 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. 9433
    Prev
    Next
    INDEX
    Explanations

    at email documentation

    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
    .wik
    -0.07
    apper
    -0.07
    heet
    -0.07
    imiz
    -0.07
    etz
    -0.07
    ÙĨب
    -0.07
    nock
    -0.07
    aler
    -0.07
     Cove
    -0.07
    æ¦Ľ
    -0.07
    POSITIVE LOGITS
    ä¸Ģè¨Ģ
    0.07
    ä¸Ģäºĭ
    0.07
    太ä¸Ĭ
    0.07
    æľīå¾ħ
    0.07
    ä¸Ģéģĵ
    0.07
    ago
    0.07
    好å¤ĦçļĦ
    0.06
    ä¸Ģæŀļ
    0.06
    æ¿Ģèµ·
    0.06
    åıijè¨Ģ稿
    0.06
    Activations Density 0.003%

    No Known Activations