© 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. 28232
    Prev
    Next
    INDEX
    Explanations

    verb "argue" and its forms

    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
    Playable
    -0.08
    mier
    -0.08
    ä»»ä½ł
    -0.07
    被称为
    -0.07
    éĤ£åı¯æĺ¯
    -0.07
    溪éķĩ
    -0.07
     reportedly
    -0.07
    建设éĽĨåĽ¢æľīéĻIJåħ¬åı¸
    -0.07
    _assigned
    -0.07
    UTO
    -0.07
    POSITIVE LOGITS
    åIJĪçIJĨæĢ§
    0.08
     bahwa
    0.08
    çIJĨçĶ±
    0.07
     rằng
    0.07
    以ä¸ĭåĩłçĤ¹
    0.07
     uniqueness
    0.07
    istically
    0.07
     argue
    0.07
    çļĦå®īåħ¨æĢ§
    0.07
     why
    0.07
    Activations Density 0.005%

    No Known Activations