© 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. 7954
    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
    åįİ丽
    -0.28
     guests
    -0.28
    槿
    -0.27
    ä¸Ģ页
    -0.25
    add
    -0.25
    å¸Ŀ
    -0.24
     beste
    -0.24
    [block
    -0.24
    åľ°ä¸Ńæµ·
    -0.23
    rif
    -0.23
    POSITIVE LOGITS
     therm
    0.27
    phas
    0.26
    iances
    0.25
    neys
    0.24
    .SO
    0.24
    layers
    0.24
     niż
    0.24
    nock
    0.24
     phil
    0.24
    _zeros
    0.24
    Activations Density 0.023%

    No Known Activations

    This feature has no known activations.