© 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. 111201
    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
    Negative Logits
    dÃŃ
    -0.29
    iasco
    -0.27
    Formats
    -0.27
     disagreed
    -0.27
    CTest
    -0.26
    rometer
    -0.26
    imeter
    -0.25
    ä¸İåIJ¦
    -0.25
    èĨı
    -0.25
    partials
    -0.24
    POSITIVE LOGITS
    los
    0.26
     des
    0.26
    åºĶåıĬæŶ
    0.25
    imson
    0.25
    æĶĴ
    0.24
     paralyzed
    0.24
     missing
    0.24
     paired
    0.24
     der
    0.23
    æĤ¬
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.