© 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. 43551
    Prev
    Next
    INDEX
    Explanations

    cytoskeletal organization and assembly

    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
     worse
    -0.08
    SQL
    -0.08
    鼶
    -0.07
    sql
    -0.07
    èĹı
    -0.07
     worst
    -0.07
    æľºç»Ħ
    -0.07
    太åŃIJ
    -0.07
    èĸ°
    -0.07
    ucket
    -0.07
    POSITIVE LOGITS
    å¤ĸåIJij
    0.08
    æľºåĬ¨
    0.08
     remodeling
    0.08
     mobi
    0.08
    åij¨éķ¿
    0.08
    hesion
    0.08
     mảng
    0.08
    è°ĥæݧ
    0.08
    éĶļ
    0.08
    ltk
    0.08
    Activations Density 0.128%

    No Known Activations