© 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. 39428
    Prev
    Next
    INDEX
    Explanations

    recognition

    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
    errat
    -0.27
    !’
    -0.26
     Caldwell
    -0.26
     ||↵
    -0.26
     vic
    -0.25
    agers
    -0.25
    earer
    -0.25
    ||||
    -0.24
    ||(
    -0.24
    糧
    -0.24
    POSITIVE LOGITS
    æ·¡åĮĸ
    0.26
    bane
    0.26
    GF
    0.25
    ÑĦи
    0.25
     schedule
    0.25
    åĪĿ次
    0.25
    å²³
    0.24
    schedule
    0.24
     schedules
    0.24
     hearts
    0.24
    Activations Density 0.373%

    No Known Activations