© 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. 7678
    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
    é¦ĸåħĪæĺ¯
    -0.27
     %@
    -0.27
    符åIJĪæĿ¡ä»¶
    -0.25
    æĹ¢è¦ģ
    -0.25
    ä¸įä»ħè¦ģ
    -0.25
    Official
    -0.25
    ä¸įæŃ¢
    -0.24
     invo
    -0.24
     official
    -0.24
    endale
    -0.24
    POSITIVE LOGITS
    chen
    0.28
    (feature
    0.27
     holds
    0.27
    ige
    0.26
    borough
    0.25
    feature
    0.24
    æĹłç¼ĺ
    0.24
    ottle
    0.24
    holds
    0.23
    avis
    0.23
    Activations Density 0.256%

    No Known Activations

    This feature has no known activations.