© 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. 108538
    Prev
    Next
    INDEX
    Explanations

    code

    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
    ugu
    -0.28
    aws
    -0.28
     incl
    -0.27
    avel
    -0.27
    onom
    -0.26
    icks
    -0.26
    clus
    -0.26
    acks
    -0.26
    çŃĶåį·
    -0.25
    ún
    -0.25
    POSITIVE LOGITS
    æĬ¬å¤´
    0.28
    รà¸Ń
    0.26
    zia
    0.25
    太åŃIJ
    0.25
    GetMethod
    0.25
    ItemId
    0.24
    æĬ¬èµ·å¤´
    0.24
    ãĥ©ãĥ³ãĥī
    0.24
    extended
    0.24
    è¿Ļç¬Ķ
    0.24
    Activations Density 1.839%

    No Known Activations