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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 6522
    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
     existing
    -0.28
    ä¿Ŀ
    -0.27
    ее
    -0.27
    åİŁ
    -0.27
    eca
    -0.26
     AND
    -0.26
    ’
    -0.26
    otic
    -0.25
    ó
    -0.25
    m
    -0.25
    POSITIVE LOGITS
     Rif
    0.29
    iless
    0.29
    俱ä¹IJéĥ¨
    0.27
    comings
    0.26
    èŀ¨
    0.26
     disproportion
    0.26
     naw
    0.25
     yeti
    0.24
    [${
    0.24
    è¡£çī©
    0.24
    Activations Density 0.037%

    No Known Activations

    This feature has no known activations.