© 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. 20-TRANSCODER-HP
    7. 106815
    Prev
    Next
    INDEX
    Explanations

    Time or narrative progression

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     transition
    -0.26
    coli
    -0.25
    uD
    -0.25
    ueur
    -0.25
    oods
    -0.24
    inez
    -0.24
    tres
    -0.24
    transition
    -0.24
     transitions
    -0.24
    erce
    -0.23
    POSITIVE LOGITS
    Meanwhile
    0.57
    åı¦ä¸Ģæĸ¹éĿ¢
    0.56
     Meanwhile
    0.53
    åı¦ä¸Ģè¾¹
    0.50
    ä¸İæѤåIJĮæŶ
    0.47
    åı¦ä¸Ģ
    0.45
     concurrently
    0.45
    åIJĮæŶ
    0.44
     meanwhile
    0.43
     simultaneously
    0.43
    Activations Density 43.337%

    No Known Activations