© 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. 64395
    Prev
    Next
    INDEX
    Explanations

    verbs followed by impact adverbs

    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
    æį®è¯´
    -0.09
    opan
    -0.08
    hopefully
    -0.08
    åIJĮä¸Ĭ
    -0.08
    天åīį
    -0.08
    _border
    -0.07
    sure
    -0.07
    _expired
    -0.07
    ä¹Łæĺ¯ä¸ºäºĨ
    -0.07
     endless
    -0.07
    POSITIVE LOGITS
     surprisingly
    0.10
    æŀľçĦ¶
    0.10
    ç«ŁçĦ¶
    0.10
    ä¸į论æĺ¯
    0.09
    æŀľçĦ¶æĺ¯
    0.09
    å±ħçĦ¶æĺ¯
    0.08
    å±ħçĦ¶
    0.08
    ç«ŁçĦ¶æĺ¯
    0.08
     indeed
    0.08
     neither
    0.08
    Activations Density 1.090%

    No Known Activations