© 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. 8494
    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
    对èĩªå·±çļĦ
    -0.28
    ä¸įåŃĺåľ¨
    -0.27
    ously
    -0.26
    .Stack
    -0.25
     SEAL
    -0.25
    è´¨éĩıåĴĮ
    -0.25
    çļĦè´¨éĩı
    -0.25
    åIJįèªī
    -0.24
    roys
    -0.24
    輩
    -0.24
    POSITIVE LOGITS
    .section
    0.27
    .’
    0.25
     Vive
    0.24
    åıĺ
    0.24
     grosse
    0.24
     Dorm
    0.24
     dorm
    0.24
    ä¸Ģ段
    0.23
    tics
    0.23
    _subtitle
    0.23
    Activations Density 0.853%

    No Known Activations

    This feature has no known activations.