© 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. 8490
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    æľīæŶåĢĻ
    -0.09
    æľīäºĽ
    -0.09
    好åĥı
    -0.09
    æľīåħ³äººåijĺ
    -0.08
    æĦıæĢĿ
    -0.08
    æĪĸèĢħåħ¶ä»ĸ
    -0.08
    åľ¨éĤ£
    -0.07
    èĩ
    -0.07
    æĭ¿
    -0.07
    å¦ĤæŀľæĬĬ
    -0.07
    POSITIVE LOGITS
    å°ıè§ij
    0.08
    èĩ³åħ³éĩįè¦ģ
    0.08
    onton
    0.08
    è¿Ļä¸įä»ħ
    0.08
    驱åĬ¨çļĦ
    0.08
    åį³åı¯èİ·å¾Ĺ
    0.07
    çĭŀ
    0.07
    模åĿĹåĮĸ
    0.07
    便å°Ĩ
    0.07
    æ®Ĩå°½
    0.07
    Activations Density 0.000%

    No Known Activations