© 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. 24279
    Prev
    Next
    INDEX
    Explanations

    bilinear transform

    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
     Hav
    -0.07
    aine
    -0.06
    aign
    -0.06
     nug
    -0.06
    仿çĶŁ
    -0.06
    çĥĽ
    -0.06
     xuyên
    -0.06
    亲
    -0.06
    ä¸įæĮ¯
    -0.06
    踪影
    -0.06
    POSITIVE LOGITS
    ymmetric
    0.08
    icha
    0.08
    .sym
    0.08
     transformation
    0.08
     Sym
    0.08
    åıĺæį¢
    0.08
    transforms
    0.08
    ä¸įåİĮ
    0.08
    转åĮĸçļĦ
    0.08
    ัà¸ģษ
    0.07
    Activations Density 0.002%

    No Known Activations