© 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. 99147
    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
     spark
    -0.29
    ottom
    -0.29
    icularly
    -0.28
    illum
    -0.28
    ordering
    -0.27
    æľ¬ä¹¦
    -0.27
    ophage
    -0.25
    spark
    -0.24
     conservatism
    -0.24
    ausal
    -0.23
    POSITIVE LOGITS
    ç»·
    0.26
    å¿ĻçĿĢ
    0.25
    æ£
    0.25
    ç¼Ħ
    0.24
    æĬĺèħ¾
    0.23
    çľł
    0.23
    ä¸ĩ个
    0.23
    \core
    0.23
    ä¹ĥ
    0.23
    èİ·æĤī
    0.22
    Activations Density 0.040%

    No Known Activations

    This feature has no known activations.