© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 5293
    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
     Donetsk
    -0.28
     général
    -0.27
    箬
    -0.27
    irim
    -0.26
     general
    -0.26
    GEN
    -0.24
    Gen
    -0.24
    éķĿ
    -0.24
     Gen
    -0.24
    trade
    -0.24
    POSITIVE LOGITS
    ÑģоÑĢ
    0.27
     Reviewed
    0.26
    æĩĭ
    0.25
    HAM
    0.25
    LowerCase
    0.25
    äºİä¸Ģä½ĵ
    0.24
    yps
    0.24
    æŁ¥
    0.24
    sic
    0.24
    <![
    0.24
    Activations Density 0.271%

    No Known Activations

    This feature has no known activations.