© 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. 7202
    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
    éģĵ
    -0.29
    èĽĭçĻ½
    -0.26
    æĻ®
    -0.26
    .createTextNode
    -0.26
    ters
    -0.25
    instancetype
    -0.25
     kal
    -0.25
    eko
    -0.24
    设ç«ĭ
    -0.24
    åħħæ²Ľ
    -0.24
    POSITIVE LOGITS
    .synthetic
    0.28
    uess
    0.27
     Issue
    0.26
    (pb
    0.25
    boa
    0.25
    ari
    0.24
    holm
    0.23
    laus
    0.23
    bü
    0.23
     Ireland
    0.23
    Activations Density 0.142%

    No Known Activations

    This feature has no known activations.