© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 8564
    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
    azes
    -0.29
    æĢ§åĪ«
    -0.25
    /=
    -0.25
    ä»ĸ们ä¼ļ
    -0.25
    lname
    -0.24
     stron
    -0.24
    æĢ¯
    -0.24
    ITED
    -0.24
    çĨĽ
    -0.23
    ismic
    -0.23
    POSITIVE LOGITS
    iche
    0.27
    plet
    0.26
    ortex
    0.26
     cr
    0.26
     D
    0.26
    lasses
    0.26
    ç¹ĩ
    0.26
    Express
    0.24
    Attached
    0.24
    cam
    0.24
    Activations Density 0.042%

    No Known Activations

    This feature has no known activations.