© 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. 13567
    Prev
    Next
    INDEX
    Explanations

    linearity and bilinear properties

    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
    çĿĢçĶ¨
    -0.07
    ezz
    -0.07
    åħ¨æĸĩéĺħ读
    -0.07
    å©Ĩ
    -0.07
    Ùħص
    -0.07
     Bằng
    -0.07
    err
    -0.07
    zenten
    -0.07
    apper
    -0.06
    å®ļ为
    -0.06
    POSITIVE LOGITS
    Inputs
    0.08
     Inputs
    0.08
    enal
    0.08
     xá»Ń
    0.07
    è±ļ
    0.07
     contracted
    0.07
    owo
    0.07
    yect
    0.07
    åı¯è¨Ģ
    0.07
    ì¹Ļ
    0.07
    Activations Density 0.003%

    No Known Activations