© 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. 88764
    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
    é»Ħæĺı
    -0.31
    stär
    -0.30
    æĮĩ导æĦıè§ģ
    -0.29
    -family
    -0.28
    unting
    -0.28
    heimer
    -0.26
     Guidelines
    -0.26
    stdbool
    -0.25
    éľĢè¦ģçĶ¨
    -0.25
    rÄĻcz
    -0.25
    POSITIVE LOGITS
    thon
    0.33
     linear
    0.30
     static
    0.28
     cur
    0.28
     flat
    0.26
    ACHI
    0.26
    Linear
    0.25
     original
    0.25
     yn
    0.25
    GD
    0.25
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.