© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 5061
    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
     cur
    -0.24
     CUR
    -0.24
    Å¡t
    -0.24
     ServletException
    -0.23
    rats
    -0.23
    è¡ĮæĶ¿åĮº
    -0.23
    lain
    -0.23
     comp
    -0.23
    客æĪ·æıIJä¾Ľ
    -0.23
    oidal
    -0.22
    POSITIVE LOGITS
    iro
    0.28
    incer
    0.27
    ç¼°
    0.26
     Ont
    0.26
    dog
    0.25
    åķĸ
    0.25
    pv
    0.25
     Rhodes
    0.25
    té
    0.24
    为人
    0.24
    Activations Density 0.006%

    No Known Activations

    This feature has no known activations.