© 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. 108585
    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
    éĵ§
    -0.28
    illard
    -0.28
    enerator
    -0.27
    ovan
    -0.26
    äºĨä¸Ģ份
    -0.26
     hur
    -0.25
    arness
    -0.25
     './../../
    -0.25
    缸åħ³è´Łè´£
    -0.25
    gro
    -0.25
    POSITIVE LOGITS
    ä¸įåģļ
    0.28
    ä¸ĢæľŁ
    0.27
    æĬ¥åijĬ
    0.27
    semb
    0.26
     Äijẳng
    0.25
     mag
    0.24
     Nob
    0.24
    ç»ĦåĽ¢
    0.24
    pio
    0.24
    çłĶ究æĬ¥åijĬ
    0.23
    Activations Density 15.774%

    No Known Activations

    This feature has no known activations.