© 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. 50273
    Prev
    Next
    INDEX
    Explanations

    transitioning discourse marker

    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
    inkt
    -0.09
     бÑĥдÑĤо
    -0.08
    chner
    -0.08
    Ãłng
    -0.08
    عاÙĦ
    -0.08
    ynie
    -0.08
    ysi
    -0.08
    ow
    -0.07
    èĢĮä¸įè§ģ
    -0.07
    ä»Ģä¹Īåij¢
    -0.07
    POSITIVE LOGITS
    fatt
    0.08
    forth
    0.08
    รà¸Ļ
    0.07
    neh
    0.07
    rov
    0.07
    ÏĦÏģÏĮ
    0.07
    ãģĶç´¹ä»ĭ
    0.07
    é«ĺåĤ²
    0.07
    &w
    0.07
    laš
    0.07
    Activations Density 0.006%

    No Known Activations