© 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. 141337
    Prev
    Next
    INDEX
    Explanations

    problems, origins, functionality

    np_max-act · gemini-2.0-flash
    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
    enko
    -0.28
    社群
    -0.26
    ẩn
    -0.25
    æĬµæĬĹ
    -0.24
     Sar
    -0.23
    å¾µ
    -0.23
    æĭĵ
    -0.23
     bay
    -0.23
    橱
    -0.23
     im
    -0.23
    POSITIVE LOGITS
    ton
    0.24
     Seeder
    0.24
     newObj
    0.23
    åħ³äºİæĪij们
    0.23
    IGH
    0.23
    çıº
    0.23
    ocos
    0.23
    STALL
    0.23
     fortunes
    0.23
    å¹¶åľ¨
    0.23
    Activations Density 41.780%

    No Known Activations