© 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. 6108
    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
    itori
    -0.28
    pees
    -0.27
     foul
    -0.27
    otine
    -0.26
    æĪĸå¤ļ
    -0.25
    elier
    -0.25
    olut
    -0.24
    éģ¹
    -0.24
    inia
    -0.24
    pector
    -0.24
    POSITIVE LOGITS
    ä¸ĢæŃ¥æŃ¥
    0.28
    cast
    0.26
    _keywords
    0.26
    广
    0.25
    åIJĪ
    0.25
     Osw
    0.24
    翼
    0.24
     Demon
    0.24
    ngine
    0.24
    keywords
    0.24
    Activations Density 0.009%

    No Known Activations

    This feature has no known activations.