© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 6992
    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
    Not in Any Lists

    No Comments

    Negative Logits
     {}.
    -0.31
    顺çĿĢ
    -0.29
    .cert
    -0.27
    æĪIJåĬŁçļĦ
    -0.26
    vez
    -0.25
    bz
    -0.25
    lique
    -0.25
    ari
    -0.25
    boards
    -0.24
     conclude
    -0.24
    POSITIVE LOGITS
     autos
    0.34
     Autos
    0.29
    æĮĤ
    0.26
    æľĪä¸Ń
    0.25
    ias
    0.25
    pong
    0.25
     negatives
    0.24
     crossorigin
    0.24
    ?=.*
    0.24
     fabric
    0.24
    Activations Density 0.004%

    No Known Activations

    This feature has no known activations.