© 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. 129007
    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
    hum
    -0.29
    çĵ¤
    -0.25
    è¾Ĥ
    -0.25
    åIJİåı°
    -0.25
     herself
    -0.24
    CHIP
    -0.24
    _superuser
    -0.23
    ä¸Ģæĸ¹
    -0.23
    ä¸Ģç¬ij
    -0.23
    _allocator
    -0.23
    POSITIVE LOGITS
    æĿľåħ°
    0.26
    à¹Ģย
    0.25
    feeds
    0.25
    CRET
    0.25
     cer
    0.25
    YNC
    0.24
    çľ¼åīį
    0.24
    æľīæĿ¡ä»¶
    0.24
    ä¼łåĩº
    0.24
    è¿Ħ
    0.24
    Activations Density 0.003%

    No Known Activations

    This feature has no known activations.