© 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. 131029
    Prev
    Next
    INDEX
    Explanations

    Holiday

    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
    èĢĮåİ»
    -0.27
    ä¹Łè¦ģ
    -0.26
    èѦæĥķ
    -0.26
    å¸ĪçĶŁ
    -0.25
    coln
    -0.24
     realise
    -0.24
     realised
    -0.24
    èľĺèĽĽ
    -0.23
    ä¸İåħ¶ä»ĸ
    -0.23
    anuts
    -0.23
    POSITIVE LOGITS
    æݾ
    0.27
    erde
    0.26
    åIJįåįķ
    0.24
     commit
    0.24
    éĻ¢éķ¿
    0.24
    该éĻ¢
    0.24
    #c
    0.23
    losed
    0.23
    åij
    0.23
    stra
    0.23
    Activations Density 1.522%

    No Known Activations