© 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. 142600
    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
     IEEE
    -0.26
    rai
    -0.25
     rej
    -0.24
     cray
    -0.24
     blow
    -0.24
    è½½
    -0.23
    alem
    -0.23
    稷
    -0.23
    æĵ¦
    -0.23
    ('^
    -0.23
    POSITIVE LOGITS
    ĶåĽŀ
    0.31
     Pence
    0.26
    istinguish
    0.26
    Ħ件
    0.25
    amarin
    0.25
    éĥ¯
    0.24
    ihad
    0.24
    Im
    0.24
     lightly
    0.24
     pData
    0.24
    Activations Density 0.329%

    No Known Activations

    This feature has no known activations.