© 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. 50551
    Prev
    Next
    INDEX
    Explanations

    font family and size

    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
    以ä¸Ĭå°±æĺ¯å°ıç¼ĸ
    -0.08
    oire
    -0.08
    мÑĥм
    -0.08
    踵
    -0.07
    欢è¿İ广大
    -0.07
    æľīçĶ¨çļĦ
    -0.07
     prostata
    -0.07
    æĹłéĹ»
    -0.07
    ergen
    -0.07
    oretical
    -0.07
    POSITIVE LOGITS
    asikan
    0.08
    ़
    0.08
    noinspection
    0.08
    awesome
    0.08
    rijk
    0.08
    ainment
    0.07
     lá»ĵ
    0.07
    stash
    0.07
    Ïį
    0.07
    ØŃÙĨ
    0.07
    Activations Density 0.021%

    No Known Activations