© 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. 54988
    Prev
    Next
    INDEX
    Explanations

    command line arguments

    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
    utorials
    -0.08
    erschein
    -0.07
    chter
    -0.07
    ãģıãģł
    -0.07
    å¾ĢæľŁåĽŀ顾
    -0.07
    typings
    -0.07
    ianas
    -0.07
    iaan
    -0.07
    å±ĪæĮĩ
    -0.07
    iel
    -0.07
    POSITIVE LOGITS
    æĩĴ
    0.07
    è¿Ļ便æĺ¯
    0.07
    åĨīåĨī
    0.06
    æĹłåIJį
    0.06
    é«ĺéĽħ
    0.06
    å«©
    0.06
    ä¸ĢåĪĩéĥ½æĺ¯
    0.06
    æĪijè¦ģ
    0.06
    è¿ĻäºĽéĥ½æĺ¯
    0.06
     input
    0.06
    Activations Density 0.001%

    No Known Activations