© 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. 52158
    Prev
    Next
    INDEX
    Explanations

    remove the following

    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
    åį³çĶ¨
    -0.07
    æľīéģĵ
    -0.07
    åĽĽæĺŁ
    -0.07
    open
    -0.06
    obuf
    -0.06
    mend
    -0.06
    纫
    -0.06
    _counter
    -0.06
    bed
    -0.06
     Counter
    -0.06
    POSITIVE LOGITS
    åīįåIJİ
    0.12
    å½¼æѤ
    0.11
    å½¼æѤçļĦ
    0.10
    åīįåIJİçļĦ
    0.10
    ä¸İåħ¶ä»ĸ
    0.10
    pairs
    0.10
     pairs
    0.10
    åįĹåĮĹ
    0.10
    åIJĮ士
    0.10
     ìĦľë¡ľ
    0.09
    Activations Density 0.280%

    No Known Activations