© 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. 39661
    Prev
    Next
    INDEX
    Explanations

    the

    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
    Fixture
    -0.27
    人ãģ¨
    -0.26
    andler
    -0.24
    arget
    -0.24
    åIJĪå½±
    -0.24
     brush
    -0.24
     brushed
    -0.23
    ador
    -0.23
    stitial
    -0.23
     teamed
    -0.23
    POSITIVE LOGITS
    åĺĺ
    0.29
    ä¸Ģç«Ļ
    0.29
    éĩĮç¨ĭ
    0.27
     PRIV
    0.26
    åģĪ
    0.25
    SY
    0.25
    upp
    0.25
    stairs
    0.25
    å¹³åı°ä¸Ĭ
    0.25
    lernen
    0.25
    Activations Density 0.681%

    No Known Activations