© 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. 10372
    Prev
    Next
    INDEX
    Explanations

    pattern for `(`

    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
     ÙĪاÙĦتÙĬ
    -0.08
     ÙĪاÙĦØ°ÙĬ
    -0.08
     which
    -0.07
    ilet
    -0.07
     à¸ĭึà¹Īà¸ĩมี
    -0.07
     à¸ĭึà¹Īà¸ĩà¸Īะ
    -0.07
    which
    -0.07
    —which
    -0.07
    å¦Ĥä½ķå°Ĩ
    -0.07
     à¸ĭึà¹Īà¸ĩ
    -0.07
    POSITIVE LOGITS
    åĽłä¸ºå®ĥ
    0.10
    æĺ¯åĽłä¸º
    0.09
    ä½ķåĨµ
    0.08
     because
    0.08
    èĢĮä¸Ķæľī
    0.08
    èĬ±ä¸Ģ
    0.08
    because
    0.08
     Ãĩünkü
    0.07
    çĶļèĩ³æ¯Ķ
    0.07
    èĢĮä¸Ķæĺ¯
    0.07
    Activations Density 0.054%

    No Known Activations