© 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. 8421
    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
     mee
    -0.27
     cape
    -0.26
    usc
    -0.25
     Commentary
    -0.25
     sor
    -0.25
    æ¢ħ西
    -0.25
    å®ļ
    -0.24
     Nicol
    -0.24
    æĮĩåIJij
    -0.24
    ä¸ĸçķĮçļĦ
    -0.23
    POSITIVE LOGITS
    achers
    0.27
    enser
    0.26
     seats
    0.26
    æĪªæŃ¢
    0.25
    è¾ħ导åijĺ
    0.24
    ailability
    0.24
    :green
    0.24
     diets
    0.23
    ä¸Ŀ
    0.23
    StreamReader
    0.23
    Activations Density 0.004%

    No Known Activations

    This feature has no known activations.