© 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. 18521
    Prev
    Next
    INDEX
    Explanations

    break down, away with, break the mold

    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¸įå¾ĹäºĨ
    -0.07
    éĶĻè¿ĩäºĨ
    -0.07
     ÙħØ´Ú©
    -0.07
    å°ıåĪ°
    -0.07
    åıĬéĻĦåĬł
    -0.07
    å°ijéĩıçļĦ
    -0.07
    ä½ļ
    -0.06
    管çIJĨåѦéĻ¢
    -0.06
    å¦Ĥçģ«
    -0.06
    åĢ¼æѤ
    -0.06
    POSITIVE LOGITS
    åİŁæľīçļĦ
    0.14
    åİŁåħĪ
    0.12
    ä¼łç»Ł
    0.12
    åĽºæľīçļĦ
    0.11
    åİŁæľī
    0.11
    ä¼łç»ŁçļĦ
    0.11
     traditional
    0.11
    å¾ĵæĿ¥ãģ®
    0.11
    以å¾ĢçļĦ
    0.11
    以å¾Ģ
    0.10
    Activations Density 0.150%

    No Known Activations