© 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. 20-TRANSCODER-HP
    7. 141398
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sach
    -0.29
     bull
    -0.29
    ä¿ĿåŃĺ
    -0.25
    çļĦæīĢæľī
    -0.25
    åIJĮæĥħ
    -0.25
    åīįæĸ¹
    -0.24
    ัà¸į
    -0.24
     FCC
    -0.24
    acci
    -0.24
    nestjs
    -0.24
    POSITIVE LOGITS
    onda
    0.26
    amas
    0.26
    ermo
    0.26
    æīª
    0.26
    ked
    0.26
    年以æĿ¥
    0.26
    .Raise
    0.25
    wiki
    0.25
    å«©
    0.25
     ìķĦëĭĪëĭ¤
    0.24
    Activations Density 2.247%

    No Known Activations

    This feature has no known activations.