© 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. 37722
    Prev
    Next
    INDEX
    Explanations

    Asked Questions

    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
     przecież
    -0.08
    æĹ¢æľī
    -0.08
    ưỡng
    -0.08
     genu
    -0.07
     ÑıкобÑĭ
    -0.07
    éĤ£ä¹Ī容æĺĵ
    -0.07
    éĤ£ä¹Īå°±
    -0.07
     whatever
    -0.07
    ocup
    -0.07
    .removeListener
    -0.07
    POSITIVE LOGITS
    åıĬåĪ©æģ¯
    0.07
    æĹ¥çĶŁ
    0.07
    åıĬè¦ģæ±Ĥ
    0.07
    主ãģª
    0.07
    åĨħ容åıĬ
    0.07
    oidal
    0.07
    é¡¹çĽ®åıĬ
    0.07
    oad
    0.07
     –
    0.07
    æĬĢæľ¯åıĬ
    0.06
    Activations Density 0.080%

    No Known Activations