© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 19130
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and numbers

    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
    odb
    -0.08
    inga
    -0.07
     oldest
    -0.07
    大çĪ±
    -0.07
     fullest
    -0.07
    ivin
    -0.06
    èĪªç«Ļ
    -0.06
     secr
    -0.06
    æľĢç¾İçļĦ
    -0.06
     Ici
    -0.06
    POSITIVE LOGITS
    éļ¾æĢª
    0.09
    æĢªä¸įå¾Ĺ
    0.08
     realistic
    0.08
    itzer
    0.08
    çĶ±æѤåı¯è§ģ
    0.07
     clearly
    0.07
    éľĢè¦ģèĢĥèĻij
    0.07
     ample
    0.07
     realistically
    0.07
    æĮģè¯ģ
    0.07
    Activations Density 0.023%

    No Known Activations