© 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. 19-TRANSCODER-HP
    7. 9651
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    reh
    -0.24
    æľ¯è¯Ń
    -0.24
     experimental
    -0.24
    sparse
    -0.24
     vess
    -0.24
    CHK
    -0.24
    è¿Ļ两
    -0.23
    üh
    -0.23
     Experimental
    -0.23
    ÑĢоз
    -0.23
    POSITIVE LOGITS
     bra
    0.30
    bau
    0.27
    æĹ¥çĶµ
    0.26
     slu
    0.25
    wp
    0.24
     gew
    0.24
     variation
    0.24
    ä¹Łè®©
    0.24
     convergence
    0.24
    inst
    0.23
    Activations Density 0.004%

    No Known Activations

    This feature has no known activations.