© 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. 22-TRANSCODER-HP
    7. 128942
    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_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    åºŁ
    -0.26
     gr
    -0.26
     es
    -0.25
    ricks
    -0.25
    æł¼
    -0.25
    ngen
    -0.24
    çĶµç«Ļ
    -0.24
    .vn
    -0.24
     ticking
    -0.24
    ible
    -0.24
    POSITIVE LOGITS
     Slater
    0.30
    ä¸ĸçķĮä¸ĬæľĢ
    0.26
    çĿ«
    0.26
    åĨįæĿ¥
    0.26
     pretend
    0.26
     Bour
    0.25
     pretended
    0.25
    ãģ¨ãģĦãģĨãĤĤãģ®
    0.24
     innoc
    0.24
    åĨį
    0.23
    Activations Density 0.001%

    No Known Activations