© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 62013
    Prev
    Next
    INDEX
    Explanations

    word 'won' followed by 't'

    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
    emu
    -0.09
    ed
    -0.08
    ation
    -0.08
    zilla
    -0.08
    allet
    -0.08
    em
    -0.08
    anju
    -0.08
    åľ¨
    -0.08
    embe
    -0.07
    express
    -0.07
    POSITIVE LOGITS
    er
    0.08
    itional
    0.08
    ä¸Ģå¦ĤæĹ¢å¾Ģ
    0.08
    ÏĦαι
    0.08
    çĦ¶æĺ¯
    0.08
    íģ¬
    0.08
    äºĪ
    0.08
     be
    0.08
    åľ¨ä»ĬåIJİ
    0.08
    mente
    0.07
    Activations Density 0.004%

    No Known Activations