© 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. 14618
    Prev
    Next
    INDEX
    Explanations

    conjunction like hence, therefore

    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
    ï¸İ
    -0.08
    ä¸įå¿ĺ
    -0.08
    efore
    -0.08
    sius
    -0.08
    theless
    -0.08
    顾åIJįæĢĿ
    -0.08
    orious
    -0.08
     Himself
    -0.08
     puis
    -0.07
     halnya
    -0.07
    POSITIVE LOGITS
    åĽłæŃ¤åľ¨
    0.07
     hence
    0.07
    åĽłèĢĮ
    0.07
    åĽłæѤ
    0.07
     therefore
    0.07
     pertanto
    0.07
    otti
    0.07
    ëĶ°
    0.07
     represents
    0.06
     daher
    0.06
    Activations Density 0.625%

    No Known Activations