© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 61900
    Prev
    Next
    INDEX
    Explanations

    code comments and strings

    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
    itte
    -0.07
    çļĦçŃĶæ¡Ī
    -0.06
    çģ¿çģ¿
    -0.06
    çİĭä¼Ł
    -0.06
    âĢİ
    -0.06
    åĩ¡æľ¬ç½ij注æĺİ
    -0.06
    anser
    -0.06
    çĦ¶æĺ¯
    -0.06
    atro
    -0.06
     adam
    -0.06
    POSITIVE LOGITS
    .Formatter
    0.07
    פש
    0.07
    iph
    0.07
    andingkan
    0.07
    zim
    0.07
    .Inject
    0.07
    elingen
    0.07
    antul
    0.07
    водÑĭ
    0.07
    ë¥
    0.07
    Activations Density 0.084%

    No Known Activations