© 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. 52499
    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
    æµ®
    -0.30
    iat
    -0.29
    åIJĮæĹ¶ä¹Łæĺ¯
    -0.28
    åį³æŶ
    -0.27
    helm
    -0.26
    尽管
    -0.26
    å¡Ķ
    -0.26
    èĢģçĪ·
    -0.26
    åĬ¡
    -0.25
    å¾ģæľį
    -0.25
    POSITIVE LOGITS
     Birthday
    0.26
    檫
    0.26
    foods
    0.25
     extrad
    0.24
    çī¡
    0.24
     opener
    0.24
    allen
    0.24
    &W
    0.24
     Bris
    0.23
     hang
    0.23
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.