© 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. 129150
    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
    éĩĮçļĦ
    -0.29
    omo
    -0.28
    åĪ·æĸ°
    -0.28
    SIDE
    -0.28
    é£İ鼨
    -0.26
    å±ķå¼Ģ
    -0.24
    æľīä½ķ
    -0.24
    fil
    -0.24
    rod
    -0.24
    igor
    -0.24
    POSITIVE LOGITS
    resentation
    0.29
    æķ¬ä¸ļ
    0.26
    jis
    0.25
    âĢ¦↵↵↵↵
    0.25
    migration
    0.25
    pare
    0.24
     contend
    0.24
    اسÙĬ
    0.24
     buff
    0.24
    ueue
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.