© 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. 6797
    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
    ysts
    -0.26
    keiten
    -0.26
    orna
    -0.25
     uns
    -0.25
     cron
    -0.25
    ily
    -0.24
    olith
    -0.24
     Cron
    -0.24
    _pack
    -0.24
    建åįİ
    -0.24
    POSITIVE LOGITS
    åĪ°è´¦
    0.29
    pecial
    0.28
    Äįe
    0.26
    ower
    0.26
     capacities
    0.25
    owered
    0.25
    潦
    0.25
    æµħ
    0.24
    åĪ«
    0.24
    æľīèī²
    0.24
    Activations Density 0.149%

    No Known Activations

    This feature has no known activations.