© 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. 31943
    Prev
    Next
    INDEX
    Explanations

    final word or phrase

    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
    æĸ°å¤©åľ°
    -0.08
    à¸ĩ
    -0.07
     initially
    -0.07
    ÙĤد
    -0.07
    æĪijæĿ¥è¯´ä¸¤åı¥
    -0.07
    èĽĽ
    -0.07
     entire
    -0.07
     intervening
    -0.07
    åİĨåı²æĤłä¹ħ
    -0.07
    天çĶŁçļĦ
    -0.07
    POSITIVE LOGITS
    çīĪçļĦ
    0.09
    ize
    0.08
    umo
    0.08
    ä¹Łæĺ¯æľĢ
    0.07
    åħ³å¤´
    0.07
    IZE
    0.07
    izing
    0.07
    ç»Ī
    0.07
    ×ķ×Ĺ
    0.07
    ligen
    0.07
    Activations Density 0.005%

    No Known Activations