© 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. 89008
    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
    ä¸ĢæĬĬ
    -0.27
     Boone
    -0.26
    اÙĨب
    -0.23
    .dc
    -0.23
     sodom
    -0.23
    åĺ»
    -0.23
    æĸ¹ä¾¿
    -0.23
     appreciated
    -0.23
    etary
    -0.23
    è¿ĺæĺ¯å¾Ī
    -0.23
    POSITIVE LOGITS
    atif
    0.27
    igr
    0.26
    xBE
    0.26
     Gra
    0.25
     gran
    0.24
     algorithm
    0.24
    usra
    0.23
    åĩºè·¯
    0.23
     GRA
    0.23
    _GRA
    0.23
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.