© 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. 57391
    Prev
    Next
    INDEX
    Explanations

    Esperanto months and days

    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
    ÄĻg
    -0.07
     overd
    -0.07
    ekar
    -0.07
    ÃĿ
    -0.07
    rega
    -0.06
    åħļåijĺçļĦ
    -0.06
     اÙĦباÙĦ
    -0.06
    actu
    -0.06
    warts
    -0.06
    ýv
    -0.06
    POSITIVE LOGITS
    享æľī
    0.07
     hÃło
    0.07
    kje
    0.07
    à¸Ķัà¸ĩ
    0.07
    ä¹Łåĸľæ¬¢
    0.06
    çIJ³å¨ľ
    0.06
     Ñģимволи
    0.06
    .Symbol
    0.06
     unsure
    0.06
    åį¿
    0.06
    Activations Density 0.026%

    No Known Activations