© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 130912
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    entials
    -0.26
    elling
    -0.25
     mot
    -0.25
    æĹłå½¢
    -0.24
     j
    -0.24
     hearty
    -0.24
     ach
    -0.24
    ä¸įéĹ´
    -0.24
    åĬ¨æľº
    -0.24
    èķĥ
    -0.23
    POSITIVE LOGITS
    æīĢæıIJä¾Ľ
    0.27
    æıIJä¾ĽäºĨ
    0.25
     PROVIDED
    0.25
    æıIJä¾Ľ
    0.24
    /flutter
    0.24
    jong
    0.24
    avic
    0.24
    provided
    0.24
    æıIJä¾ĽçļĦ
    0.24
     provided
    0.24
    Activations Density 0.014%

    No Known Activations

    This feature has no known activations.