© 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. 562
    Prev
    Next
    INDEX
    Explanations

    embedding and partition

    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
    åĩłå£°
    -0.07
    åĩ»
    -0.06
    urn
    -0.06
     vast
    -0.06
    relevant
    -0.06
    .scan
    -0.06
    å®ĪåĪĻ
    -0.06
     awaiting
    -0.06
    åıĺåĮĸåĴĮ
    -0.06
    rof
    -0.06
    POSITIVE LOGITS
    çļĦåŃĺåľ¨
    0.12
    åŃĺåľ¨çļĦ
    0.11
     Exists
    0.10
     exists
    0.10
     existência
    0.10
    æĺ¯åIJ¦åŃĺåľ¨
    0.09
    ãģĮåŃĺåľ¨
    0.09
    .exists
    0.09
     ÑģÑĥÑīеÑģÑĤво
    0.09
    exists
    0.09
    Activations Density 0.044%

    No Known Activations