© 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. 670
    Prev
    Next
    INDEX
    Explanations

    FEDERAL CLAIMS

    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
    åĴ«å°º
    -0.07
    occhi
    -0.06
    å¹´å¤ļ
    -0.06
    indari
    -0.06
     ich
    -0.06
     beyond
    -0.06
    ail
    -0.06
    åѦéĻ¢
    -0.06
    ya
    -0.06
    oz
    -0.06
    POSITIVE LOGITS
    å¼ģ
    0.08
    ç«Ļç«Ļ
    0.08
    Contained
    0.08
    çĽ
    0.08
    itesse
    0.08
    urette
    0.08
    elon
    0.08
    eluk
    0.07
    dos
    0.07
    isting
    0.07
    Activations Density 0.022%

    No Known Activations