© 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. 151438
    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
    suppress
    -0.25
    cratch
    -0.24
     wink
    -0.24
    ʺ
    -0.24
    *sizeof
    -0.24
    -Aug
    -0.23
     blackmail
    -0.23
    âĸĪâĸĪâĸĪâĸĪ
    -0.23
    !("
    -0.23
     humming
    -0.22
    POSITIVE LOGITS
    离åİ»
    0.29
     advanced
    0.27
    åĪĽæĦı
    0.26
    indhoven
    0.25
    çķĻä¸ĭ
    0.25
    aturas
    0.25
     leaves
    0.24
    éĽ¢ãĤĮ
    0.24
    离å¼ĢäºĨ
    0.24
     leaving
    0.24
    Activations Density 1.184%

    No Known Activations

    This feature has no known activations.