© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 16070
    Prev
    Next
    INDEX
    Explanations

    stable xenon

    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
    ä¿
    -0.08
    -port
    -0.08
    acas
    -0.07
    ãĥĿãĥ¼ãĥĪ
    -0.07
    endor
    -0.07
    WO
    -0.07
    /port
    -0.07
    ارب
    -0.07
    enburg
    -0.07
    chwitz
    -0.06
    POSITIVE LOGITS
     darin
    0.08
    å½ĵåľ°
    0.07
    åľ¨æīĢ
    0.07
    æĥ³è¦ģåľ¨
    0.07
    黼
    0.07
    .localization
    0.07
    olut
    0.06
    èľľæľĪ
    0.06
    æĥ³åİ»
    0.06
    ette
    0.06
    Activations Density 0.668%

    No Known Activations