© 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. 64820
    Prev
    Next
    INDEX
    Explanations

    Code and licenses

    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
    ragments
    -0.26
    /***************************************************************************↵
    -0.25
     prospect
    -0.25
    åıĪ好
    -0.25
     sights
    -0.24
    QT
    -0.24
    olley
    -0.24
    AndView
    -0.24
    maries
    -0.24
     Cro
    -0.23
    POSITIVE LOGITS
     Op
    0.27
    æ¥ŀ
    0.25
    Op
    0.25
    Ob
    0.24
    éļİ
    0.24
    ãģ®ãģĤãĤĭ
    0.24
    .Pod
    0.24
    ippers
    0.24
    (Op
    0.24
     diesen
    0.23
    Activations Density 5.886%

    No Known Activations