© 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. 14-TRANSCODER-HP
    7. 41690
    Prev
    Next
    INDEX
    Explanations

    punctuation/stopwords

    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
    Negative Logits
    óg
    -0.27
    碰
    -0.27
    keleton
    -0.24
    /disable
    -0.24
     adequ
    -0.24
    vvm
    -0.23
    itledBorder
    -0.23
    è¿Ļ家ä¼Ļ
    -0.23
    åIJİèĢħ
    -0.23
    _dirty
    -0.23
    POSITIVE LOGITS
    Threads
    0.25
    izard
    0.25
    zan
    0.25
     wart
    0.24
     ÄIJá»ĵng
    0.24
    ÑĪив
    0.24
     palms
    0.24
    (clicked
    0.24
    straction
    0.24
    .fromString
    0.23
    Activations Density 0.101%

    No Known Activations