© 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. 12-TRANSCODER-HP
    7. 21973
    Prev
    Next
    INDEX
    Explanations

    Interchangability

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    hung
    -0.27
    wash
    -0.25
    üb
    -0.25
    åŁºæľ¬åİŁåĪĻ
    -0.25
    ockets
    -0.25
    çݯ
    -0.24
    åĨķ
    -0.24
    æĶ¶èİ·
    -0.24
    åѤç«ĭ
    -0.24
    sey
    -0.24
    POSITIVE LOGITS
    ä»İ严治
    0.29
    è¿Ŀ
    0.26
     dream
    0.25
    æĮ¡ä½ı
    0.25
    çļĭ
    0.25
     Klo
    0.25
    ",-
    0.24
     deal
    0.24
    .Dispatcher
    0.24
     Cr
    0.24
    Activations Density 0.002%

    No Known Activations