© 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. 44176
    Prev
    Next
    INDEX
    Explanations

    last name titles

    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
    åľ¨å½ĵæŶ
    -0.07
    åѦæĬ¥
    -0.07
    lover
    -0.07
     erect
    -0.07
     erected
    -0.07
    è¦ģ使
    -0.07
    èĭĽ
    -0.06
    ortal
    -0.06
    çĥŃçģ«
    -0.06
     clumsy
    -0.06
    POSITIVE LOGITS
    æľ¬èģĮ
    0.09
    çİ°ä»»
    0.08
    æľ¬èģĮå·¥ä½ľ
    0.07
    å±¥
    0.07
    soles
    0.07
     founding
    0.07
    .linkedin
    0.07
    çݰ为
    0.07
    ç»ıéªĮ丰å¯Į
    0.07
    å±¥åİĨ
    0.07
    Activations Density 1.245%

    No Known Activations