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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 6434
    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
    Unnamed
    -0.29
     Narc
    -0.26
    éªĤ
    -0.25
     Amb
    -0.25
    代çIJĨ
    -0.25
     qualitÃł
    -0.25
     Babe
    -0.25
     reps
    -0.24
     dated
    -0.24
     departments
    -0.23
    POSITIVE LOGITS
    apers
    0.29
    ä»ĸä»¬åľ¨
    0.28
    onor
    0.26
    ç±³ç²ī
    0.25
    ä»ĸ们æĺ¯
    0.25
    acements
    0.25
    ål
    0.25
    çļĦè¶ĭåĬ¿
    0.24
    ersen
    0.24
    okus
    0.24
    Activations Density 0.109%

    No Known Activations

    This feature has no known activations.