© 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. 130865
    Prev
    Next
    INDEX
    Explanations

    technical content

    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
    Not in Any Lists

    No Comments

    Negative Logits
    .latest
    -0.27
    ä»ĸä»¬åľ¨
    -0.25
    aron
    -0.25
    æ¯Ķ
    -0.24
     lle
    -0.24
     inter
    -0.24
    ament
    -0.24
    Anywhere
    -0.23
    NAMESPACE
    -0.23
    .animation
    -0.23
    POSITIVE LOGITS
    çļĭ
    0.27
    IBC
    0.26
    uty
    0.25
    称ä¹ĭ
    0.25
    ardu
    0.25
    å¼ķé¢Ĩ
    0.25
    ä¼łè¨Ģ
    0.24
    ówki
    0.24
    idal
    0.24
    bling
    0.24
    Activations Density 5.026%

    No Known Activations