© 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. 108648
    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
     Sword
    -0.29
     converters
    -0.27
     WINDOWS
    -0.26
    åħħåĢ¼
    -0.25
    WINDOWS
    -0.25
    plural
    -0.25
     vaccines
    -0.25
    åĬłåĢį
    -0.24
    ä¸ĢäºĮ
    -0.24
    åıijåĶ®
    -0.24
    POSITIVE LOGITS
    _sid
    0.27
    å°Ĩèĩªå·±çļĦ
    0.26
    宣
    0.26
    注éĩį
    0.25
     }}/
    0.24
    ä¸į失
    0.24
    ="__
    0.24
     Fig
    0.24
    åIJİåį«
    0.24
    ighth
    0.24
    Activations Density 87.160%

    No Known Activations

    This feature has no known activations.