© 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. 34760
    Prev
    Next
    INDEX
    Explanations

    public class

    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
    iveness
    -0.08
    isman
    -0.07
    enberg
    -0.07
    æķĻèĤ²è¡ĮæĶ¿éĥ¨éŨ
    -0.07
    ä¹ĭåīij
    -0.07
     sights
    -0.07
     wonder
    -0.07
    amani
    -0.07
    orda
    -0.07
    ÙĪÛĮÛĮ
    -0.07
    POSITIVE LOGITS
     class
    0.07
     terbak
    0.07
     nadr
    0.07
    _BATCH
    0.07
     rumpe
    0.07
     kuin
    0.07
    _WRAP
    0.07
    elor
    0.06
    _COMPILE
    0.06
    .CreateDirectory
    0.06
    Activations Density 0.078%

    No Known Activations