© 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. 7039
    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
    arro
    -0.27
    å±ī
    -0.25
     disemb
    -0.25
    çļĦè¿ĽæŃ¥
    -0.25
     Transitional
    -0.25
    à¸Ńà¸Ļ
    -0.24
     Ingram
    -0.24
     uncon
    -0.24
    èĽĽ
    -0.24
    åįĥåı¤
    -0.23
    POSITIVE LOGITS
    uez
    0.27
    亲
    0.26
    oc
    0.25
    æľº
    0.25
    ix
    0.25
    ä¸Ģ段
    0.25
    os
    0.25
     syll
    0.24
     OC
    0.24
    æĹ¢æľī
    0.24
    Activations Density 0.064%

    No Known Activations

    This feature has no known activations.