© 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. 4981
    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
    /octet
    -0.28
    Gatt
    -0.25
    èIJ½åľ¨
    -0.25
    ä¹Łä¸įä¾ĭå¤ĸ
    -0.24
    utta
    -0.24
    (fin
    -0.24
    åį«
    -0.24
    åĪĨæł¡
    -0.24
    æĹ¢è¦ģ
    -0.24
    aki
    -0.24
    POSITIVE LOGITS
    elt
    0.24
    .drive
    0.24
    pawn
    0.24
    ibern
    0.23
     Oper
    0.23
    ________________________________________________________________
    0.23
    intern
    0.23
    äºĨå¾Īå¤ļ
    0.23
    ate
    0.23
    åºŁçī©
    0.23
    Activations Density 0.250%

    No Known Activations

    This feature has no known activations.