© 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. 64709
    Prev
    Next
    INDEX
    Explanations

    type

    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
     Toro
    -0.27
    .wrap
    -0.27
    æĥ³èµ·
    -0.26
    _attachment
    -0.25
    ãģĬé¡ĺãģĦ
    -0.24
    itelist
    -0.24
    åį´åıĪ
    -0.23
    führen
    -0.23
    _look
    -0.23
    floating
    -0.23
    POSITIVE LOGITS
    lab
    0.31
     lab
    0.29
    å¦Ĥæľīä¾µæĿĥ
    0.27
     Lab
    0.25
    åıĮåIJij
    0.25
    Lab
    0.25
    _DECLARE
    0.25
    ÑĤе
    0.24
    åķ¡
    0.24
    å®ŀéªĮ室
    0.24
    Activations Density 5.186%

    No Known Activations