© 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. 37640
    Prev
    Next
    INDEX
    Explanations

    hack, ack, inequality

    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
     Leban
    -0.08
     LATIN
    -0.08
    åı°ä¸Ń
    -0.07
    stur
    -0.07
    åĿŀ
    -0.07
    æ²Ĥ
    -0.07
    åĽŀéģĵ
    -0.07
    оне
    -0.07
    æ·¡æ·¡
    -0.07
    ç»ĵæŀĦ设计
    -0.07
    POSITIVE LOGITS
     inversion
    0.08
    iab
    0.08
     inequalities
    0.08
    ä¸įçŃī
    0.07
    anou
    0.07
     inequality
    0.07
     reversal
    0.07
     multiplication
    0.07
     monot
    0.07
    irsch
    0.07
    Activations Density 0.008%

    No Known Activations