© 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. 1649
    Prev
    Next
    INDEX
    Explanations

    statistical topics

    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
     dÃłng
    -0.08
    quiera
    -0.08
    /disable
    -0.08
    ãĤĴæŀľãģŁ
    -0.08
     technologique
    -0.08
    äºijéľĦ
    -0.07
    atismo
    -0.07
    wards
    -0.07
    ÑīеÑĤ
    -0.07
    liness
    -0.07
    POSITIVE LOGITS
    istical
    0.13
    ively
    0.10
    æĦıä¹īä¸ĬçļĦ
    0.09
    icians
    0.08
    ANDARD
    0.08
    -cultural
    0.08
    ally
    0.08
     kê
    0.08
    ypes
    0.07
    uale
    0.07
    Activations Density 0.021%

    No Known Activations