© 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. 33-TRANSCODER-HP
    7. 54593
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ixed
    -0.27
     Cemetery
    -0.26
    æľĪ以æĿ¥
    -0.26
    æľīæĿ¡ä»¶çļĦ
    -0.26
     Loose
    -0.26
    hk
    -0.25
    nice
    -0.25
    edu
    -0.24
    ivative
    -0.24
    following
    -0.24
    POSITIVE LOGITS
    å°±æĺ¯è¿Ļæł·
    0.25
    #w
    0.25
     express
    0.25
    aint
    0.24
     outward
    0.24
    ä¸ĢåľĪ
    0.24
    åıªèĥ½
    0.24
    ö
    0.24
    erge
    0.24
    зд
    0.24
    Activations Density 0.004%

    No Known Activations

    This feature has no known activations.