© 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. 19-TRANSCODER-HP
    7. 9668
    Prev
    Next
    INDEX
    Explanations

    kind

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    å¾Īæ·±
    -0.23
    vero
    -0.23
     obsc
    -0.22
     quo
    -0.22
    .nb
    -0.21
    âĿ®
    -0.21
    æĹłéĻIJ
    -0.21
    opers
    -0.21
    ä¸įå·²
    -0.21
     popular
    -0.21
    POSITIVE LOGITS
    eners
    0.27
    led
    0.26
    æĢ§æł¼
    0.25
    ake
    0.24
    OfMonth
    0.24
    æĿIJ
    0.24
    ening
    0.24
    velop
    0.23
    lia
    0.23
    иÑĩ
    0.23
    Activations Density 0.966%

    No Known Activations