© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 58781
    Prev
    Next
    INDEX
    Explanations

    phrases ending in "on" or "@"

    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
     likewise
    -0.08
     similarly
    -0.08
    ä¸¹ä¸ľ
    -0.07
     altrimenti
    -0.07
     otherwise
    -0.07
    æĸĹç½Ĺ
    -0.07
    ä¸ĢæĿ¡è¡Ĺ
    -0.07
    亦æĺ¯
    -0.07
    è§Ħå®ļçļĦåħ¶ä»ĸ
    -0.07
    ×ķתר
    -0.07
    POSITIVE LOGITS
    åīįèĢħ
    0.15
    åIJİèĢħ
    0.14
     latter
    0.12
    两èĢħ
    0.10
    äºĮèĢħ
    0.10
     predominantly
    0.08
    ãģ©ãģ¡ãĤī
    0.08
    åģıåIJij
    0.08
    å¤ļæķ°
    0.08
    第ä¸īç§į
    0.08
    Activations Density 0.122%

    No Known Activations