© 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. 6937
    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
    arters
    -0.27
    åĴ¬
    -0.27
    olina
    -0.27
     Marble
    -0.26
    ocha
    -0.26
     restraint
    -0.25
    TOT
    -0.25
    adamente
    -0.24
    ongan
    -0.24
     vain
    -0.24
    POSITIVE LOGITS
     dag
    0.26
    ä¸įå®ļ
    0.26
    xp
    0.24
    xde
    0.24
    bars
    0.24
    ãĤ¿ãĥ«
    0.24
    -js
    0.24
     neur
    0.23
    stärke
    0.23
     WEIGHT
    0.23
    Activations Density 0.028%

    No Known Activations

    This feature has no known activations.