© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 130977
    Prev
    Next
    INDEX
    Explanations

    technical/medical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    çīĮ
    -0.28
    RODUCTION
    -0.26
    sse
    -0.25
    éķ¿æķĪ
    -0.25
    etics
    -0.25
    MAS
    -0.25
     bearings
    -0.25
    ìºIJ
    -0.25
    shots
    -0.25
    URY
    -0.25
    POSITIVE LOGITS
    crease
    0.25
    typ
    0.25
    åĨį说
    0.24
    åİŁåĪĻ
    0.24
    .sensor
    0.24
    ATERIAL
    0.24
     Alic
    0.24
    åIJĮå¿ĥ
    0.24
    èµĸ
    0.23
    æľīåĩłä¸ª
    0.23
    Activations Density 0.060%

    No Known Activations