© 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. 24700
    Prev
    Next
    INDEX
    Explanations

    Cell and cell-related terms

    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
    item
    -0.08
    -item
    -0.07
    untr
    -0.07
    è¯ļæĮļ
    -0.07
    åįĥåįĥä¸ĩ
    -0.07
    unicode
    -0.07
    yadi
    -0.07
    ä¸įåħ¥
    -0.07
    érique
    -0.07
    _decl
    -0.07
    POSITIVE LOGITS
    ç»Ĩèĥŀ
    0.09
     Cells
    0.09
     cells
    0.09
     Cell
    0.09
    ç»ĨèĥŀçļĦ
    0.08
    ç´°èĥŀ
    0.08
    cells
    0.08
     cell
    0.08
    Cells
    0.08
    -cell
    0.08
    Activations Density 0.013%

    No Known Activations