© 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. 63607
    Prev
    Next
    INDEX
    Explanations

    years, anniversary, generations, centuries, weeks

    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
     Madura
    -0.08
    ä¸Ģæĸ¹
    -0.08
    kirchen
    -0.08
     minlength
    -0.08
    çĭŃ
    -0.08
    stantiate
    -0.08
    åģ¥åĦ¿
    -0.08
     raro
    -0.08
    клик
    -0.08
    udo
    -0.08
    POSITIVE LOGITS
     successive
    0.09
     elapsed
    0.08
     consecutive
    0.08
     suces
    0.07
     подÑĢÑıд
    0.07
    è¿Ń
    0.06
     cumulative
    0.06
    secutive
    0.06
     (-
    0.06
    åıłåĬł
    0.06
    Activations Density 0.001%

    No Known Activations