© 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. 8063
    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
    é»ij马
    -0.26
    ç£ķ
    -0.25
    xcd
    -0.25
    jsonp
    -0.25
    zew
    -0.25
    пÑĥÑĤ
    -0.24
    ableView
    -0.24
    овиÑĩ
    -0.24
    ophage
    -0.23
    opi
    -0.23
    POSITIVE LOGITS
    lights
    0.27
    âĮĪ
    0.25
    åĪĨ
    0.24
    <u
    0.24
    ken
    0.24
    /share
    0.24
    stück
    0.24
    è¿Ļæł·ä¸Ģ个
    0.23
    ãĥĪãĥ¬
    0.23
     maxim
    0.23
    Activations Density 0.039%

    No Known Activations

    This feature has no known activations.