© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 12793
    Prev
    Next
    INDEX
    Explanations

    negation and exclusion

    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
    åĩĨåŃĹ
    -0.08
    çŁ¥éģĵæĪij
    -0.08
    ĥĿ
    -0.07
    obl
    -0.07
    ä¸įä¹ħçļĦ
    -0.07
    ffen
    -0.07
    only
    -0.07
    ettel
    -0.07
    uvia
    -0.07
    ä½ķçŃī
    -0.07
    POSITIVE LOGITS
    æĪĸå°ij
    0.08
     yet
    0.07
    è¦Ĩ
    0.07
    ä¼ĺç¾İ
    0.06
     biá»ĩt
    0.06
    å¤ªè¿ľ
    0.06
     بÙĥØ«ÙĬر
    0.06
    å±ŀäºİèĩªå·±çļĦ
    0.06
    ÑģÑģи
    0.06
    第ä¸Ģè´¢ç»ı
    0.06
    Activations Density 0.058%

    No Known Activations