© 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. 7855
    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
    éłĵ
    -0.27
    ä½Ĩæĺ¯å¯¹äºİ
    -0.26
    anus
    -0.26
    illion
    -0.25
    imate
    -0.25
    hta
    -0.25
    æīĪ
    -0.25
    üler
    -0.24
    หมาย
    -0.24
    ä½Ĩæĺ¯ä»ĸ
    -0.24
    POSITIVE LOGITS
    Confirmed
    0.28
     lord
    0.28
    ari
    0.27
    Lord
    0.27
     Lord
    0.27
     confirming
    0.27
     lords
    0.26
    åĽ½éĺ²
    0.26
     BASIS
    0.25
    Available
    0.25
    Activations Density 0.068%

    No Known Activations

    This feature has no known activations.