© 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. 9477
    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
    edo
    -0.27
    æħ£
    -0.25
    iren
    -0.25
    ESCO
    -0.25
     implicitly
    -0.24
    è½Ń
    -0.24
    acellular
    -0.24
    implicitly
    -0.24
    -ing
    -0.23
     Euros
    -0.23
    POSITIVE LOGITS
    ä¸įå°½
    0.32
    æĬ±
    0.29
    ä¸į代表
    0.27
    ãĤ¢ãĤ¦ãĥĪ
    0.26
    ä¸įèµ·
    0.25
    éĹ´çļĦ
    0.25
    nte
    0.25
    çĦ°
    0.24
    stack
    0.24
     Pars
    0.24
    Activations Density 0.294%

    No Known Activations

    This feature has no known activations.