© 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. 6457
    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
     special
    -0.27
    ãĤ¤ãĥ¡ãĥ¼ãĤ¸
    -0.27
     Dr
    -0.26
    avic
    -0.26
    acket
    -0.26
     Special
    -0.26
    ç©´
    -0.24
     intuit
    -0.24
     av
    -0.24
    IGO
    -0.24
    POSITIVE LOGITS
     embarrassed
    0.29
    çģŃ
    0.27
    临
    0.26
     Feinstein
    0.26
     Convers
    0.26
    =edge
    0.26
    essional
    0.25
    urbation
    0.25
    Conversation
    0.25
    ÑĢем
    0.25
    Activations Density 0.090%

    No Known Activations

    This feature has no known activations.