© 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. 34875
    Prev
    Next
    INDEX
    Explanations

    Nelson, numbers, acronyms

    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
    Negative Logits
    两大
    -0.07
    çģ¯
    -0.07
    æĸ¹
    -0.07
    ä¸ī大
    -0.07
    éĴĵ
    -0.06
    æĴµ
    -0.06
    åĽĽå¤§
    -0.06
    uw
    -0.06
    emat
    -0.06
    å¿ł
    -0.06
    POSITIVE LOGITS
    åĬłè½½æĽ´å¤ļ
    0.09
    à´ĸ
    0.08
    ringer
    0.08
    è¯ĿæĿ¥
    0.08
    èĬ±æŀľ
    0.08
    åķĨä¸ļçĶ¨éĢĶ
    0.08
    adura
    0.08
     cale
    0.08
    以赴
    0.08
    ontan
    0.07
    Activations Density 0.049%

    No Known Activations