© 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. 110959
    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
    [Index
    -0.27
    require
    -0.27
    _WE
    -0.24
    .require
    -0.24
    æĢ»å±Ģ
    -0.24
     ense
    -0.24
    (bl
    -0.24
    åī²
    -0.23
    æħİéĩį
    -0.23
    箩
    -0.23
    POSITIVE LOGITS
    hy
    0.28
    .ali
    0.27
    her
    0.25
    igne
    0.25
    heim
    0.25
     rubbing
    0.24
    hol
    0.24
    alty
    0.24
     Thompson
    0.24
     thresh
    0.24
    Activations Density 0.048%

    No Known Activations

    This feature has no known activations.