© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 9139
    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
    aways
    -0.28
    ä¸ĩæĪ·
    -0.26
     ofType
    -0.26
    Wiki
    -0.25
    éĢļçķħ
    -0.25
    asions
    -0.24
    èİ«åIJį
    -0.24
    !!!↵↵
    -0.24
     BMC
    -0.24
    åIJ¸å¼ķ
    -0.24
    POSITIVE LOGITS
    rium
    0.30
     italic
    0.27
     shar
    0.27
     borderTop
    0.25
    -cost
    0.25
    cum
    0.25
    -tools
    0.24
    uish
    0.24
     Studio
    0.24
    sharp
    0.24
    Activations Density 1.084%

    No Known Activations

    This feature has no known activations.