© 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. 108609
    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
     shred
    -0.27
    çļĩ家
    -0.26
     Wax
    -0.26
    严
    -0.25
    æĿ¥ä¸´
    -0.24
    误导
    -0.24
    éķ¿èĢģ
    -0.24
    åĪ°æĿ¥
    -0.23
    èľľ
    -0.23
    protocols
    -0.23
    POSITIVE LOGITS
    kel
    0.27
    \Has
    0.27
    ï¼Ł↵↵
    0.25
    burgh
    0.25
     Winners
    0.24
    ÐĶÐķ
    0.24
    ----------↵↵
    0.24
    manuel
    0.24
    acias
    0.24
     chance
    0.24
    Activations Density 28.117%

    No Known Activations

    This feature has no known activations.