© 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. 7352
    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
    teen
    -0.27
    å²Ĥ
    -0.26
    éĴĿ
    -0.26
    дÑĢа
    -0.26
    amp
    -0.26
    åı¬éĽĨ
    -0.25
    æݪ
    -0.24
     substance
    -0.24
    mine
    -0.24
    建设
    -0.24
    POSITIVE LOGITS
    ilon
    0.30
    eria
    0.28
    ByKey
    0.25
    gam
    0.24
    istical
    0.24
    istique
    0.23
    åĵ¡
    0.23
    大çĨĬçĮ«
    0.23
     committing
    0.23
    bers
    0.23
    Activations Density 0.808%

    No Known Activations

    This feature has no known activations.