© 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. 7183
    Prev
    Next
    INDEX
    Explanations

    numbers, Estonia, renal

    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
    åīįèĢħ
    -0.06
    åľ¨ç»ıè¿ĩ
    -0.06
     shim
    -0.06
     uncomp
    -0.06
    estro
    -0.06
     Peyton
    -0.06
    ç¿
    -0.06
    IF
    -0.06
    Ïĩα
    -0.06
    RF
    -0.06
    POSITIVE LOGITS
     itself
    0.11
    æľ¬èº«çļĦ
    0.11
    æľ¬èº«
    0.11
     himself
    0.11
    æľ¬èº«å°±æĺ¯
    0.11
     themselves
    0.11
    æľ¬èº«å°±
    0.10
    ä»ĸèĩªå·±çļĦ
    0.10
    ä»ĸèĩªå·±
    0.10
    æĪijèĩªå·±
    0.10
    Activations Density 0.020%

    No Known Activations