© 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. 86756
    Prev
    Next
    INDEX
    Explanations

    academic/technical content

    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
     trade
    -0.28
     TRADE
    -0.27
     Ka
    -0.26
     Trade
    -0.25
    itr
    -0.24
    åľ°çĤ¹
    -0.24
    iface
    -0.24
    ider
    -0.24
     radi
    -0.24
    |%
    -0.24
    POSITIVE LOGITS
    thinkable
    0.29
     synopsis
    0.27
     Nationals
    0.26
    .Usage
    0.26
    atomy
    0.25
    lords
    0.25
    ä¸į对
    0.24
    ardon
    0.24
    _usage
    0.24
    artment
    0.24
    Activations Density 0.003%

    No Known Activations