© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 30147
    Prev
    Next
    INDEX
    Explanations

    research/scientists/study

    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
    ulary
    -0.08
    _examples
    -0.08
    Thunder
    -0.08
    æ¯Ĵèį¯
    -0.07
    çĦ¶æĺ¯
    -0.07
    رÙĬض
    -0.07
    åľ°ä¸»
    -0.07
    èĢĮå½Ĵ
    -0.07
     misd
    -0.07
    eneral
    -0.07
    POSITIVE LOGITS
     researchers
    0.12
    çłĶ究人åijĺ
    0.12
     research
    0.10
    çłĶ究
    0.10
     scientists
    0.09
    Researchers
    0.09
    research
    0.09
    çļĦçłĶ究
    0.09
     Researchers
    0.09
    çłĶ究ä¸Ń
    0.09
    Activations Density 0.823%

    No Known Activations