© 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. 7683
    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
     prompt
    -0.29
    çĦ¶æĺ¯
    -0.26
    graphics
    -0.25
    ç²²
    -0.25
     arts
    -0.25
    åĺĪ
    -0.25
    åIJĪãĤıãģĽ
    -0.25
    TeX
    -0.25
    .createElement
    -0.24
     μ
    -0.23
    POSITIVE LOGITS
    éĻħ
    0.30
    åİŁæľīçļĦ
    0.28
    æł¹æľ¬
    0.26
     Mid
    0.26
    åİŁæľī
    0.26
    çĤĺ
    0.25
    æĻ¶ä½ĵ
    0.25
    欢
    0.25
    htt
    0.24
     rendition
    0.24
    Activations Density 0.326%

    No Known Activations

    This feature has no known activations.