© 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. 7361
    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
     extents
    -0.26
     bisc
    -0.25
    ãģ®æĸ¹ãģĮ
    -0.25
    _namespace
    -0.24
    ifie
    -0.24
    AMESPACE
    -0.24
    Benef
    -0.24
    社ä¼ļåĮĸ
    -0.24
     Ingen
    -0.24
    styl
    -0.23
    POSITIVE LOGITS
    深深çļĦ
    0.30
    幸ç¦ı
    0.25
    orst
    0.25
    ure
    0.25
    Conference
    0.24
    uptime
    0.24
    Dup
    0.24
    <?↵
    0.24
    âĪ
    0.24
    >(_
    0.23
    Activations Density 0.006%

    No Known Activations

    This feature has no known activations.