© 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. 13390
    Prev
    Next
    INDEX
    Explanations

    commas and parentheses

    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
     غÙĬرÙĩ
    -0.08
    rir
    -0.08
    æīĢ以ä»ĸ
    -0.08
    ãĤĪãģĨãģ§ãģĻãģĮ
    -0.08
    å¤ļç§įå½¢å¼ı
    -0.08
    æīĢ以æĪij们
    -0.08
    ä½Ĩä¸įæĺ¯
    -0.08
    å¤ļç§įæĸ¹å¼ı
    -0.08
     Posted
    -0.07
     vele
    -0.07
    POSITIVE LOGITS
    beck
    0.09
     oppure
    0.08
     oraz
    0.08
    以åıĬ
    0.08
    以åıĬä¸ĢäºĽ
    0.07
    以åıĬåħ¶ä»ĸ
    0.07
    该æĢİä¹ĪåĬŀ
    0.07
    åıĪæĪĸèĢħ
    0.07
     ÙĪاÙĦتÙĬ
    0.06
     balk
    0.06
    Activations Density 0.170%

    No Known Activations