© 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. 51893
    Prev
    Next
    INDEX
    Explanations

    number of occurrences, series, minimum cost

    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
    起订
    -0.07
    æīįæľīäºĨ
    -0.07
    abox
    -0.06
    å¨ģ
    -0.06
    ä»İä¸ŃåĽ½
    -0.06
     pie
    -0.06
    åĬłåĭĴ
    -0.06
    ãģĶãģ¨
    -0.06
    å®£ä¼łçīĩ
    -0.06
    åı¯ä»¥è¿Ľè¡Į
    -0.06
    POSITIVE LOGITS
    gart
    0.08
    hofer
    0.07
    -chief
    0.07
    -reply
    0.07
    èĭ±æĸĩåIJįåŃĹ
    0.07
    atra
    0.07
    endum
    0.07
    -sale
    0.07
    ampo
    0.07
    IVER
    0.07
    Activations Density 0.003%

    No Known Activations