© 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. 49677
    Prev
    Next
    INDEX
    Explanations

    next to each other

    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
    resher
    -0.09
    Æ¡
    -0.08
    kreis
    -0.08
    thu
    -0.08
    rays
    -0.07
     trá»Ŀi
    -0.07
     Independ
    -0.07
     balances
    -0.07
    æ²īæµ®
    -0.07
    acce
    -0.07
    POSITIVE LOGITS
    ç´§å¯Ĩ
    0.13
    缸éĤ»
    0.12
    æĹłç¼Ŀ
    0.11
     впл
    0.11
     adjacent
    0.11
    ç´§éĤ»
    0.10
     adjoining
    0.10
    æĮ¨
    0.10
    缸æİ¥
    0.10
    éļĻ
    0.10
    Activations Density 0.060%

    No Known Activations