© 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. 7965
    Prev
    Next
    INDEX
    Explanations

    theological, theologian, -ologist, theology

    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
    è½®æį¢
    -0.07
    weit
    -0.07
    ãĥıãĥ©
    -0.07
    ideographic
    -0.07
     independent
    -0.07
     Konto
    -0.07
    kilde
    -0.06
    æĵ¦å¹²
    -0.06
    ungle
    -0.06
    Boundary
    -0.06
    POSITIVE LOGITS
    enal
    0.07
    论è¯ģ
    0.07
    euse
    0.07
    åıĹçIJĨ
    0.07
    Å¡el
    0.07
    ecom
    0.07
    åħĭéļ¾
    0.07
     Aqu
    0.07
    é¹Ĭ
    0.07
    umus
    0.07
    Activations Density 0.006%

    No Known Activations