© 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. 65428
    Prev
    Next
    INDEX
    Explanations

    applicable principles and methods

    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
    ê±´ìĿĺ
    -0.07
    (kind
    -0.06
    ?action
    -0.06
    rof
    -0.06
    äºĨæĮĩ
    -0.06
    ystone
    -0.06
    ysql
    -0.06
    åħ¬æĬ¥
    -0.06
    å»ĵ
    -0.06
    交éĢļéĥ¨
    -0.06
    POSITIVE LOGITS
    对éĤ£äºĽ
    0.11
    éĢĤçĶ¨äºİ
    0.10
    éģ©çĶ¨æĸ¼
    0.09
    éĢĤçĶ¨çļĦ
    0.09
    æĺ¯éĴĪ对
    0.09
    åıijçĶŁäºİ
    0.08
     applicable
    0.08
    主è¦ģéĴĪ对
    0.08
    éĴĪ对
    0.08
    éĩĿå°į
    0.08
    Activations Density 0.381%

    No Known Activations