© 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. 26752
    Prev
    Next
    INDEX
    Explanations

    complex formation and binding

    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
    éĶ¤çĤ¼
    -0.08
    æĢĿéĩı
    -0.07
    æŃ¦ä¾¯
    -0.07
    zil
    -0.06
    å¾ĭå·±
    -0.06
    éŁŃ
    -0.06
    ç¾Ĭ
    -0.06
    _Element
    -0.06
    عÙĪÙĨ
    -0.06
    æķ²åĵį
    -0.06
    POSITIVE LOGITS
     %[
    0.09
    åĩºæ¸¸
    0.08
    formation
    0.08
    à¸Ĥัà¸Ļ
    0.08
    /preferences
    0.08
    ç¼Ķ
    0.08
     cosy
    0.08
    æŀģ强
    0.08
    絡
    0.07
    é¥Ń
    0.07
    Activations Density 0.010%

    No Known Activations