© 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. 14-TRANSCODER-HP
    7. 40804
    Prev
    Next
    INDEX
    Explanations

    Stephen

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aways
    -0.29
    laden
    -0.28
     streaming
    -0.27
    enci
    -0.27
    merce
    -0.26
    ãng
    -0.26
     streamed
    -0.25
     jams
    -0.25
     liners
    -0.25
    queeze
    -0.24
    POSITIVE LOGITS
    æıIJ款
    0.29
     benchmark
    0.28
     italic
    0.27
    æľºä¼ļ
    0.26
     BSD
    0.25
    ä¸Ĭåīį
    0.25
     Girls
    0.25
    å²ģ以ä¸Ĭ
    0.25
    Benchmark
    0.25
    çŃĩ
    0.24
    Activations Density 0.194%

    No Known Activations