© 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. 24-TRANSCODER-HP
    7. 149218
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    éº»æľ¨
    -0.28
    iture
    -0.28
    å±ĢéĻIJ
    -0.27
     equivalents
    -0.25
    полÑĮ
    -0.24
     Licence
    -0.24
    对åħ¶çľŁå®ŀ
    -0.24
    åķĨåĵģæĪ¿
    -0.24
     ucwords
    -0.24
    thic
    -0.23
    POSITIVE LOGITS
    arsity
    0.29
    actual
    0.27
    æĬľ
    0.25
    (sock
    0.24
     drive
    0.24
     actual
    0.24
    ardown
    0.24
     computational
    0.24
    åı¯è§ģ
    0.23
    opped
    0.23
    Activations Density 0.018%

    No Known Activations

    This feature has no known activations.