© 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. 108733
    Prev
    Next
    INDEX
    Explanations

    Diverse text

    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
     viá»ĩn
    -0.30
    èĬ®
    -0.27
     mine
    -0.26
    ãģ©ãģĨãģĦãģĨ
    -0.26
    égor
    -0.25
    æĢİ
    -0.24
    ä»ĸæĽ¾
    -0.24
     Pirate
    -0.24
    佺
    -0.23
    对åħ¶è¿Ľè¡Į
    -0.23
    POSITIVE LOGITS
     anyways
    0.28
    ::.
    0.27
     +↵↵
    0.26
     /↵↵
    0.25
    ç®±
    0.24
    ä¸ĩä¸Ģ
    0.24
     <:
    0.24
    moid
    0.24
    æĬ¥åijĬ
    0.24
    Touches
    0.23
    Activations Density 2.087%

    No Known Activations