© 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. 25098
    Prev
    Next
    INDEX
    Explanations

    you and i

    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
    afka
    -0.07
    oard
    -0.07
    è¿ŀ
    -0.07
    engg
    -0.07
    æį
    -0.06
    andu
    -0.06
    è¯¥æľº
    -0.06
    orgen
    -0.06
     conform
    -0.06
    REAM
    -0.06
    POSITIVE LOGITS
    为ä»ĸ们
    0.10
    对ä»ĸ们
    0.08
    ç»Ļä»ĸ们
    0.08
    ÙĥÙħ
    0.08
    åľ¨ä»ĸ们
    0.08
    åijĬè¯īä»ĸ们
    0.08
    帮åĬ©ä»ĸ们
    0.08
    ä¸İä»ĸ们
    0.07
    ä»ĸ们认为
    0.07
    åħ¬å®³
    0.07
    Activations Density 0.464%

    No Known Activations