© 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. 8987
    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
    Ĥ¬
    -0.33
     case
    -0.28
    丰满
    -0.26
     neph
    -0.26
    eph
    -0.24
     quickest
    -0.24
    çľĭçĿĢ
    -0.24
     rem
    -0.24
    å¸Ī
    -0.24
     Case
    -0.23
    POSITIVE LOGITS
    ervative
    0.28
    äºĨä»ĸçļĦ
    0.27
    Por
    0.25
    æĴ¬
    0.25
    paint
    0.24
    sitemap
    0.24
     MaterialApp
    0.24
    flation
    0.24
    tro
    0.24
    _por
    0.24
    Activations Density 0.119%

    No Known Activations

    This feature has no known activations.