© 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. 9459
    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
    ataka
    -0.30
    paring
    -0.26
    åįģæľĪ
    -0.26
    åĨ¬
    -0.25
    <?=
    -0.24
    ложений
    -0.23
    ("@
    -0.23
    æļ¹
    -0.23
    _=
    -0.23
    âĸ³
    -0.23
    POSITIVE LOGITS
    æĮ½
    0.25
    omatic
    0.25
    ä½ľåĵģ
    0.25
    åŃĹåı·
    0.25
    .byId
    0.25
     Petr
    0.25
    itte
    0.25
    ä¸Ģ次æĢ§
    0.24
     scrim
    0.24
     arrang
    0.24
    Activations Density 0.819%

    No Known Activations

    This feature has no known activations.