© 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. 62783
    Prev
    Next
    INDEX
    Explanations

    Conversational/technical discussions

    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
    åĽłä¸ºæĪij们
    -0.31
    åĽłä¸º
    -0.31
    åĽłä¸ºå®ĥ
    -0.28
    because
    -0.28
    uzzi
    -0.28
    åĽłä¸ºä»ĸ
    -0.28
    åı¦æľī
    -0.28
    ä¹Łæĺ¯å¦ĤæѤ
    -0.27
    åĬ¨æīĭ
    -0.27
    eval
    -0.26
    POSITIVE LOGITS
     definitely
    0.29
    orning
    0.26
    æľīä¿¡å¿ĥ
    0.25
     Legendary
    0.24
    serter
    0.24
     gros
    0.24
    uvre
    0.24
    á¹ħ
    0.24
    ãĤªãĤ¹ãĤ¹ãĥ¡
    0.24
     cél
    0.23
    Activations Density 59.584%

    No Known Activations