© 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. 63429
    Prev
    Next
    INDEX
    Explanations

    order of computational terms

    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
    /gpl
    -0.07
    ìĹ°
    -0.07
    елеÑĦ
    -0.07
    igas
    -0.07
    sla
    -0.07
     torch
    -0.06
    å¾·çļĦ
    -0.06
    纵
    -0.06
     Pulitzer
    -0.06
    سÙĩ
    -0.06
    POSITIVE LOGITS
    è½®æį¢
    0.08
     modulo
    0.08
     longest
    0.08
    æľĢçŁŃ
    0.08
    æľĢéķ¿çļĦ
    0.07
    modulo
    0.07
     تاÙħ
    0.07
    çķĶ
    0.07
    æľĢéķ¿
    0.07
    次
    0.07
    Activations Density 0.003%

    No Known Activations