© 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. 131035
    Prev
    Next
    INDEX
    Explanations

    all

    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
    个å°ı
    -0.26
    åı¯çŁ¥
    -0.26
    ÅŁehir
    -0.25
    Unit
    -0.25
    éªĸ
    -0.25
    _Unit
    -0.24
    éľĩ
    -0.24
    igsaw
    -0.24
    æİĸ
    -0.24
     baked
    -0.24
    POSITIVE LOGITS
    oland
    0.27
    space
    0.27
    ABEL
    0.26
     Leopard
    0.26
    abled
    0.25
    /logging
    0.25
    iens
    0.25
     ultimately
    0.25
     rep
    0.25
     wishing
    0.24
    Activations Density 4.800%

    No Known Activations