© 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. 110909
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    .ones
    -0.25
     yi
    -0.24
    supported
    -0.24
     supported
    -0.24
    icide
    -0.23
    庸
    -0.23
    -http
    -0.23
     warmed
    -0.23
    ä¸Ģ页
    -0.23
    åıįè¿ĩæĿ¥
    -0.23
    POSITIVE LOGITS
    åľ°ä¸ĭ
    0.29
    åĴ»
    0.28
    驺
    0.26
     stiff
    0.26
    loon
    0.25
    ottle
    0.25
    ucher
    0.25
    _locator
    0.24
    伶
    0.24
    çĤ¹
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.