© 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. 48443
    Prev
    Next
    INDEX
    Explanations

    Japanese animation studio K

    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
     constate
    -0.07
     hòn
    -0.07
    stown
    -0.07
    èĢĥçļĦ
    -0.07
    lund
    -0.07
     enunci
    -0.06
     δικ
    -0.06
    èĢĥé¢ĺ
    -0.06
    ivor
    -0.06
     اÙĦÙħÙĪ
    -0.06
    POSITIVE LOGITS
    以身
    0.08
    åĸľ
    0.07
    åħīæĺİ
    0.07
    海天
    0.06
    iej
    0.06
    å¨
    0.06
    iever
    0.06
    æĮĩåIJį
    0.06
    cano
    0.06
    indow
    0.06
    Activations Density 0.001%

    No Known Activations