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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 7156
    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
    ä¸ĢåĪ»
    -0.26
    :url
    -0.25
    ât
    -0.25
    lâ
    -0.25
    åľ°éģĵ
    -0.25
    oggled
    -0.24
    askan
    -0.24
    ;base
    -0.24
    åĬłåĪĨ
    -0.24
     dak
    -0.24
    POSITIVE LOGITS
    beat
    0.28
     Beat
    0.27
     viewType
    0.26
     thù
    0.26
     por
    0.25
    ä¾ĿéĿł
    0.25
    ç³»ç»ŁçļĦ
    0.25
    ä¼ģä¸ļçļĦ
    0.25
    ãģĶãģĸãģĦãģ¾ãģĻ
    0.24
    imately
    0.24
    Activations Density 0.004%

    No Known Activations

    This feature has no known activations.