© 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. 44635
    Prev
    Next
    INDEX
    Explanations

    sulfur compounds

    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
    ehler
    -0.08
    çľ·
    -0.07
    dll
    -0.07
    ç£ģåĬĽ
    -0.07
    (QWidget
    -0.06
    çĵ¢
    -0.06
    éĺª
    -0.06
    èľĵ
    -0.06
    ehl
    -0.06
    atte
    -0.06
    POSITIVE LOGITS
     dioxide
    0.09
    åı£çļĦ
    0.09
    undy
    0.08
    é«ĺçŃīä¸ĵç§ijåŃ¦æł¡
    0.08
     sulfur
    0.08
    è¾¾åħĭ
    0.08
    idor
    0.08
    ç¡«åĮĸ
    0.08
    tiu
    0.08
    _POINTER
    0.08
    Activations Density 0.019%

    No Known Activations