© 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. 59901
    Prev
    Next
    INDEX
    Explanations

    Base prefixes and subsequent tokens

    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
    Negative Logits
    侯
    -0.06
    天
    -0.06
    (
    -0.06
    æĶ¿
    -0.06
    åĺ±
    -0.06
    çĺ¦èĤī
    -0.06
    æľ«
    -0.05
    æľīçļĦ
    -0.05
    缸
    -0.05
    å¾ħ
    -0.05
    POSITIVE LOGITS
    ~-
    0.09
    éļ¾ä»¥å¿ĺæĢĢ
    0.08
    åĮħåIJĥ
    0.08
    广大åħļåijĺ
    0.08
    èĻ½çĦ¶ä¸įæĺ¯
    0.08
    xAA
    0.08
    äºĭåįĬåĬŁåĢį
    0.08
    à¹Ģà¸ļา
    0.07
    ewa
    0.07
    oop
    0.07
    Activations Density 0.357%

    No Known Activations