© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 25076
    Prev
    Next
    INDEX
    Explanations

    organized efforts and careful principles

    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
    éĶ¦æ¶Ľ
    -0.10
    管çIJĨæĸ¹éĿ¢
    -0.10
    ä»»ä½ķåħ¶ä»ĸ
    -0.09
    æĪĸ以åħ¶ä»ĸæĸ¹å¼ı
    -0.08
    åħ¶ä»ĸæĸ¹å¼ı
    -0.08
    åħ¶ä»ĸçļĦ
    -0.08
    other
    -0.08
    管çIJĨåıĬ
    -0.08
     destinati
    -0.08
    åİĨåı²æĢ§
    -0.08
    POSITIVE LOGITS
     careful
    0.10
     carefully
    0.09
     meticulous
    0.08
     disciplined
    0.07
     princip
    0.07
    åĸĦçĶ¨
    0.07
     principles
    0.07
    严谨
    0.07
     keen
    0.07
     systematic
    0.07
    Activations Density 0.008%

    No Known Activations