© 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. 3407
    Prev
    Next
    INDEX
    Explanations

    numbers and separators

    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
    vard
    -0.07
    æĿIJ
    -0.07
     balanced
    -0.06
    apt
    -0.06
    ycl
    -0.06
    sink
    -0.06
    为ä¸Ĭ
    -0.06
    ä¸Ģæĺ¯è¦ģ
    -0.06
    æ¯ĵ
    -0.06
     L
    -0.06
    POSITIVE LOGITS
    ä¹Łåı¯çĽ´æİ¥
    0.12
     alternatively
    0.10
     instead
    0.09
    angler
    0.09
     invece
    0.09
    缴æİ¥ä»İ
    0.09
    ä¹Łåı¯ä»¥éĢļè¿ĩ
    0.09
    instead
    0.09
    ä¹Łè¡Į
    0.09
    åı¦
    0.08
    Activations Density 0.091%

    No Known Activations