© 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. 108618
    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
    ÑĢаб
    -0.27
    charm
    -0.26
    æŁ¥
    -0.26
    ittest
    -0.26
    弧
    -0.25
     Aud
    -0.25
    aise
    -0.25
    èĦī
    -0.24
    åIJ«
    -0.24
    使ä¹ĭ
    -0.23
    POSITIVE LOGITS
    人åĿĩ
    0.31
    æĸ¼æĺ¯
    0.27
    æłĩçļĦ
    0.27
    stead
    0.27
    äºĶéĩij
    0.26
    äºİæĺ¯
    0.26
    åı¯æݧ
    0.25
    æĢĤ
    0.25
    crow
    0.25
    renal
    0.25
    Activations Density 5.505%

    No Known Activations

    This feature has no known activations.