© 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. 41754
    Prev
    Next
    INDEX
    Explanations

    Document snippets

    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
     payloads
    -0.31
     atomic
    -0.28
    payload
    -0.28
    anke
    -0.27
    erte
    -0.27
     payload
    -0.27
    iard
    -0.27
    ýt
    -0.26
    atomic
    -0.26
    iates
    -0.26
    POSITIVE LOGITS
    Ca
    0.24
     requiring
    0.24
    uther
    0.24
    CHO
    0.23
    board
    0.23
    cate
    0.23
     thuê
    0.23
    åĬĽäºī
    0.23
    ä¸ĭæĿ¥
    0.23
    .GroupLayout
    0.23
    Activations Density 0.303%

    No Known Activations