© 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. 8083
    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
    æŀ¹
    -0.34
    çļİ
    -0.27
    èĶĵ
    -0.26
    å·¥ç¨ĭæĬĢæľ¯
    -0.26
    bose
    -0.26
    便åĪ©
    -0.26
    ä¸Ģè§Ī
    -0.25
    :disable
    -0.25
    åIJĮ缣
    -0.25
    hung
    -0.24
    POSITIVE LOGITS
    ural
    0.26
    åĵį
    0.26
    -<?
    0.26
    esp
    0.25
    ecast
    0.24
    æķ¢
    0.24
    éĩį
    0.24
    à¸Ńà¸ģ
    0.23
    è½½ä½ĵ
    0.23
    /xhtml
    0.23
    Activations Density 1.818%

    No Known Activations

    This feature has no known activations.