© 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. 108785
    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
    uni
    -0.28
    èĦ±
    -0.26
    è¦Ĩ
    -0.25
     Alb
    -0.25
    구
    -0.24
    vas
    -0.24
    ye
    -0.24
    ÑģÑĤал
    -0.24
    amel
    -0.24
    æĬľ
    -0.24
    POSITIVE LOGITS
    ressing
    0.28
    ä¸Ģè¡Į
    0.25
     Cair
    0.25
     Tmin
    0.25
    ä¸Ģæī¹
    0.24
    ĵį
    0.24
     Slam
    0.24
    çļĦåīįæıIJ
    0.24
    äºĨåIJ§
    0.24
    Dismiss
    0.24
    Activations Density 12.417%

    No Known Activations

    This feature has no known activations.