© 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. 86802
    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
    ï
    -0.29
     ï
    -0.27
    .getRaw
    -0.26
    estr
    -0.25
    âĢ¦↵
    -0.25
    ïĤ
    -0.24
     ...↵
    -0.24
     düzen
    -0.24
     âĢ¦↵↵
    -0.24
    fg
    -0.23
    POSITIVE LOGITS
    ä»Ģä¹Īåı«
    0.28
     ngữ
    0.27
    _Mod
    0.24
    ocale
    0.24
    æĬľ
    0.24
    æģĻ
    0.23
    <?=
    0.23
     Almighty
    0.23
    å¯IJ
    0.23
     Mods
    0.23
    Activations Density 0.014%

    No Known Activations

    This feature has no known activations.