© 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. 40770
    Prev
    Next
    INDEX
    Explanations

    aeros and airborne particles

    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
    çŀ³
    -0.07
    datap
    -0.07
    Insets
    -0.07
     Exclusive
    -0.06
     Gate
    -0.06
    æ°´çģ«
    -0.06
    æľīä½Ļ
    -0.06
    ìĬ¤ëŁ½ê²Į
    -0.06
    ystone
    -0.06
    çĭ°çĭŀ
    -0.06
    POSITIVE LOGITS
    æī¬å°ĺ
    0.11
    åIJ¸åħ¥
    0.11
    ç²īå°ĺ
    0.10
     inhal
    0.10
     Inhal
    0.10
     airborne
    0.09
    空æ°Ķä¸Ń
    0.09
    åij¼åIJ¸éģĵ
    0.09
    åľ¨ç©ºä¸Ń
    0.09
    空ä¸Ń
    0.09
    Activations Density 0.047%

    No Known Activations