© 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. 5162
    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
    körper
    -0.27
    \Backend
    -0.26
     pó
    -0.26
    寮
    -0.24
    éĹ
    -0.24
    court
    -0.24
    ilia
    -0.23
    tu
    -0.23
     dum
    -0.23
    åIJİåı°
    -0.23
    POSITIVE LOGITS
    èĬ±äºĨ
    0.25
    就好
    0.24
    ippi
    0.24
    жен
    0.23
    agation
    0.23
    åıªçŁ¥éģĵ
    0.23
    Ĥ¨
    0.23
    alth
    0.23
    æ¯ıæ¯ı
    0.22
    acellular
    0.22
    Activations Density 2.087%

    No Known Activations

    This feature has no known activations.