© 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. 9522
    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
     pres
    -0.28
     fence
    -0.27
     Fence
    -0.24
    lrt
    -0.24
    æ¸ħæ¥ļ
    -0.24
    mad
    -0.24
    erset
    -0.23
    mpr
    -0.23
    mobx
    -0.23
    ese
    -0.23
    POSITIVE LOGITS
    ually
    0.28
     Serg
    0.27
    htar
    0.26
    åħŃ大
    0.26
    hand
    0.26
    çļĦä¸ĢéĿ¢
    0.26
    (hand
    0.26
     hand
    0.26
     Bruins
    0.25
    atee
    0.24
    Activations Density 0.095%

    No Known Activations

    This feature has no known activations.