© 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. 20-TRANSCODER-HP
    7. 62542
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    utch
    -0.26
     Dram
    -0.26
    opian
    -0.25
    aptop
    -0.25
     nw
    -0.25
    æīĭä¸Ń
    -0.24
    身ä¸Ĭ
    -0.24
    éĶº
    -0.24
    azers
    -0.23
    æݥ管
    -0.23
    POSITIVE LOGITS
    ’S
    0.30
     ç¬
    0.24
    æ´Ĺ
    0.24
     %@
    0.24
    ä¸ĵ项
    0.24
    æĶ¾åľ¨
    0.24
    ’s
    0.23
    ESA
    0.23
     Places
    0.23
    [E
    0.23
    Activations Density 0.030%

    No Known Activations

    This feature has no known activations.