© 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. 6062
    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
    èļ¤
    -0.27
    unga
    -0.24
    æĸ°éĹ»ä¸Ńå¿ĥ
    -0.24
    è°¤
    -0.24
    .contract
    -0.24
    .GroupLayout
    -0.24
    urved
    -0.24
    haar
    -0.23
     lens
    -0.23
    æľĢåħĪè¿ĽçļĦ
    -0.23
    POSITIVE LOGITS
     Loaded
    0.29
    vic
    0.27
    Loaded
    0.27
    ева
    0.26
    loaded
    0.26
    [opt
    0.26
    çħ§
    0.25
    quot
    0.25
     Flag
    0.25
     Flags
    0.24
    Activations Density 0.045%

    No Known Activations

    This feature has no known activations.