© 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. 111063
    Prev
    Next
    INDEX
    Explanations

    Code symbols

    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
     measurable
    -0.25
    ouched
    -0.25
    elage
    -0.24
    åIJ¬äºĨ
    -0.24
     popcorn
    -0.23
    MEA
    -0.23
     antes
    -0.23
     ownership
    -0.23
     previously
    -0.23
    _pel
    -0.23
    POSITIVE LOGITS
    æĸ°æµªå¾®åįļ
    0.26
     Tata
    0.26
    esco
    0.26
    IRO
    0.26
    ür
    0.25
    æݨåĩºçļĦ
    0.24
    åĩºåħ·
    0.24
    æĶ»
    0.24
    æݨåĩº
    0.24
    Tam
    0.24
    Activations Density 0.076%

    No Known Activations