© 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. 4718
    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
    DTD
    -0.25
    éģ£
    -0.25
    argin
    -0.25
    Post
    -0.25
    ypad
    -0.24
    uki
    -0.24
     Curry
    -0.24
    brace
    -0.24
    atos
    -0.24
    RAFT
    -0.24
    POSITIVE LOGITS
     toilets
    0.28
    ween
    0.27
     cellForRowAtIndexPath
    0.26
    èĢ»
    0.25
    èmes
    0.25
     Governors
    0.25
    suite
    0.24
    åĮIJ
    0.24
     jealous
    0.24
    dn
    0.24
    Activations Density 0.050%

    No Known Activations

    This feature has no known activations.