© 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. 6811
    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
    éĹ´éļĶ
    -0.29
    è
    -0.28
    pch
    -0.26
     interval
    -0.26
    _HEAD
    -0.25
    icker
    -0.25
    buster
    -0.25
    æĦıæĦ¿
    -0.24
     bur
    -0.24
     Interval
    -0.24
    POSITIVE LOGITS
     fin
    0.35
    fin
    0.27
     rec
    0.27
    以ä¸Ĭãģ®
    0.26
    acf
    0.26
    ritis
    0.25
    ductory
    0.24
     lei
    0.24
    .ft
    0.24
    adv
    0.24
    Activations Density 0.049%

    No Known Activations

    This feature has no known activations.