© 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. 34025
    Prev
    Next
    INDEX
    Explanations

    excess concentration columns

    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
    æ±ĤçĶŁåŃĺ
    -0.08
    èĭ«
    -0.08
    ĵ¨
    -0.08
    rette
    -0.08
    ä¸ĢæľĿ
    -0.07
    åĨ¤æŀī
    -0.07
    agan
    -0.07
    enner
    -0.07
    èĥ½å¤Łå®ŀçİ°
    -0.07
    gre
    -0.07
    POSITIVE LOGITS
    ä¸įèĥ½ä½ľä¸º
    0.09
    åıĸåħ¶
    0.08
    ä¸į计
    0.08
    ä¸įæĮī
    0.08
    æīĢåįł
    0.08
    常æķ°
    0.07
    åı¯ä»¥ä¸į
    0.07
    常
    0.07
    å±¥
    0.07
    å¢ŀåĩı
    0.07
    Activations Density 0.001%

    No Known Activations