© 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. 7381
    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
    ç¸
    -0.29
    æ¢Ń
    -0.28
    æĽ
    -0.27
    ä¸įä¼ļåĨį
    -0.25
    åįĩåĢ¼
    -0.25
    俸
    -0.25
    æĮº
    -0.24
    peed
    -0.24
    okies
    -0.24
    à¹ĥ
    -0.23
    POSITIVE LOGITS
     Tình
    0.28
    agate
    0.27
    åĪĨå¸ĥåľ¨
    0.26
     Moreno
    0.25
     Orient
    0.25
     dictates
    0.25
    箫
    0.24
     Reyes
    0.24
    xo
    0.24
    agit
    0.24
    Activations Density 0.155%

    No Known Activations

    This feature has no known activations.