© 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. 23476
    Prev
    Next
    INDEX
    Explanations

    representation transformation

    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
    è·µ
    -0.08
    åĨħ容æľī
    -0.07
     пÑĢоÑĪло
    -0.07
     Klin
    -0.07
    abu
    -0.07
     наилÑĥÑĩ
    -0.07
    å®Ļ
    -0.07
    è¿Ļåıª
    -0.07
    ç¥ŀé¾Ļ
    -0.07
    滥
    -0.07
    POSITIVE LOGITS
    转åĮĸ为
    0.09
    转åĮĸ
    0.09
     transform
    0.07
     transformation
    0.07
     Representation
    0.07
     Transform
    0.07
    åIJİçļĦ
    0.07
    èIJ¨æĭī
    0.07
     representation
    0.07
     Transformation
    0.07
    Activations Density 0.026%

    No Known Activations