© 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. 65348
    Prev
    Next
    INDEX
    Explanations

    thermal and physical properties

    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
    ERRUPT
    -0.08
    ãĥ³ãĥīãĥ³
    -0.07
    пей
    -0.07
    uste
    -0.07
    erschap
    -0.07
    人æĪĸ
    -0.07
    eroon
    -0.07
     Maggiore
    -0.07
    trä
    -0.07
    öt
    -0.07
    POSITIVE LOGITS
    خد
    0.07
    hini
    0.07
    owski
    0.07
    erci
    0.06
    Rgb
    0.06
    ä¹ĭéŃĤ
    0.06
    åĪĨå¸ĥå¦Ĥä¸ĭ
    0.06
    -$
    0.06
    æĸ°éĥ½
    0.06
    æķĻäºİ
    0.06
    Activations Density 0.382%

    No Known Activations