© 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. 6777
    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
     Bingo
    -0.26
    Regs
    -0.25
    rams
    -0.24
    -away
    -0.23
    č↵        č↵
    -0.23
    ä¹Ī
    -0.23
     regs
    -0.23
    udeau
    -0.23
    croft
    -0.23
    /conf
    -0.23
    POSITIVE LOGITS
    ailing
    0.33
    agenta
    0.28
    åİķ
    0.27
    ä¸įè§ģ
    0.27
    issen
    0.27
    ellow
    0.27
    alker
    0.27
    issing
    0.25
     evening
    0.25
    æĢĢæĬ±
    0.25
    Activations Density 0.173%

    No Known Activations

    This feature has no known activations.