© 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. 142764
    Prev
    Next
    INDEX
    Explanations

    of

    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
     rav
    -0.30
    èĢ³
    -0.26
     profess
    -0.26
    æĬĦ
    -0.26
     Blanco
    -0.25
    æĦıå¿Ĺ
    -0.24
     Aviv
    -0.24
    åĬŀäºĭ
    -0.24
     Essays
    -0.23
    lsi
    -0.23
    POSITIVE LOGITS
    omit
    0.28
    稷
    0.25
     omit
    0.25
    omid
    0.24
    vant
    0.24
     converse
    0.24
     diagonal
    0.23
    _it
    0.23
     dau
    0.23
    éĥĬ
    0.23
    Activations Density 6.418%

    No Known Activations