© 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. 64773
    Prev
    Next
    INDEX
    Explanations

    code snippets and file 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
    Negative Logits
     th
    -0.34
    åĩº
    -0.28
    ä¼¼
    -0.27
    ç«
    -0.27
    æ®ĸ
    -0.26
    åĨ²åĩ»
    -0.26
    atcher
    -0.26
    ansa
    -0.25
    å¿«
    -0.25
    常
    -0.25
    POSITIVE LOGITS
    ...">↵
    0.26
    åķĨçĶ¨
    0.26
    unque
    0.26
    ponce
    0.25
    _dash
    0.25
    éĬ·
    0.24
    èīº
    0.24
    åħ´æĹº
    0.24
     downloadable
    0.24
     elbow
    0.24
    Activations Density 0.844%

    No Known Activations