© 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. 2262
    Prev
    Next
    INDEX
    Explanations

    sulfur dioxide emissions from coal

    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
    举åŁİ
    -0.07
    oodles
    -0.07
    sap
    -0.07
    çĪ±å¥ĩèīº
    -0.07
     candidature
    -0.07
    ukat
    -0.07
    åľ°éĽ·
    -0.07
    åIJ¸é£Ł
    -0.07
    æļĩ
    -0.07
    ä¸Ģåı£æ°Ķ
    -0.07
    POSITIVE LOGITS
    çĩĥçħ¤
    0.09
    çħ¤
    0.09
    ulf
    0.08
     coal
    0.08
    éħ¸
    0.08
    æİĴæĶ¾
    0.08
     pyl
    0.08
    çĥŁå°ĺ
    0.08
     Coal
    0.08
    çĥŁæ°Ķ
    0.08
    Activations Density 0.029%

    No Known Activations