© 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. 44180
    Prev
    Next
    INDEX
    Explanations

    rich text control

    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
    cov
    -0.07
    ansom
    -0.07
    ycler
    -0.07
    ÑĢÑıдÑĥ
    -0.06
    nb
    -0.06
    klin
    -0.06
    åѦä¼ļ
    -0.06
    å°±ç»Ļ
    -0.06
     Trash
    -0.06
    åıįæŃ£
    -0.06
    POSITIVE LOGITS
    éĢīèĩª
    0.09
    åºĶåħ·å¤ĩ
    0.09
    åıªèĥ½æĺ¯
    0.09
    å¿ħé¡»æĺ¯
    0.09
    åĢĻè£ľ
    0.09
    å¿ħé¡»åħ·å¤ĩ
    0.09
    éĢī项ä¸Ń
    0.08
    åºĶ符åIJĪ
    0.08
    åºĶåħ·æľī
    0.08
    åı¯ä»¥æĺ¯
    0.08
    Activations Density 0.055%

    No Known Activations