© 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. 50178
    Prev
    Next
    INDEX
    Explanations

    unless, nor, except

    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
    ä¸įåıª
    -0.08
    èĢĮä¸įæĺ¯
    -0.08
    ารา
    -0.08
    ä¸įä½Ĩ
    -0.08
    gor
    -0.07
    ä¸įçĶĺ
    -0.07
    çIJĨ论ä¸İ
    -0.07
     ÙĪÙħد
    -0.07
    ä¸įæĭĺ
    -0.07
    ä¸įä»ħè¦ģ
    -0.07
    POSITIVE LOGITS
     anymore
    0.15
     melainkan
    0.13
     unless
    0.13
    unless
    0.12
    èĢĮæĺ¯
    0.12
    มาà¸ģà¸Ļัà¸ģ
    0.11
     سÙĪÙī
    0.11
     nor
    0.11
     except
    0.10
     Ø¥ÙĦا
    0.10
    Activations Density 0.095%

    No Known Activations