© 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. 63782
    Prev
    Next
    INDEX
    Explanations

    Italian greetings or phrases

    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
    åĸ·åļı
    -0.07
    ieder
    -0.07
    yster
    -0.07
    ince
    -0.07
    airo
    -0.06
    icast
    -0.06
     jel
    -0.06
    лл
    -0.06
    eter
    -0.06
    advert
    -0.06
    POSITIVE LOGITS
    å§Ĩæĸ¯
    0.07
    æĸ°çĶŁçļĦ
    0.07
    沧海
    0.07
    ampe
    0.06
    wers
    0.06
    é»ĦèĬ±
    0.06
     new
    0.06
    uent
    0.06
    abilia
    0.06
    æĸ°çĶŁ
    0.06
    Activations Density 0.021%

    No Known Activations