© 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. 42711
    Prev
    Next
    INDEX
    Explanations

    .

    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
    :bg
    -0.07
    ÙĪÙĨت
    -0.07
    ?action
    -0.07
    ÙĬØŃ
    -0.07
    ritt
    -0.07
    ÑĪип
    -0.07
    å¿ĥ缮
    -0.07
    ëŀĺ
    -0.07
    åĬłåħ¥æĶ¶èĹı
    -0.07
    лег
    -0.06
    POSITIVE LOGITS
    çĽĪçĽĪ
    0.07
    åĩĨ
    0.07
    éĸĴ
    0.07
    áli
    0.06
    æļ§
    0.06
    кÑĢа
    0.06
    %C
    0.06
    èĶ¼
    0.06
    就象
    0.06
    kie
    0.06
    Activations Density 0.063%

    No Known Activations