© 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. 149174
    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
    ebra
    -0.33
    åħ¼
    -0.25
    uxe
    -0.25
    mur
    -0.24
    uplic
    -0.23
    -up
    -0.23
     Lama
    -0.23
    åĴĮä»ĸçļĦ
    -0.23
    _factory
    -0.23
    æ²±
    -0.23
    POSITIVE LOGITS
    ahn
    0.31
    æĦŁè§īèĩªå·±
    0.29
     Hind
    0.26
    æĮº
    0.26
    赫
    0.26
     damn
    0.25
     damned
    0.25
    atum
    0.25
     pt
    0.25
    ervo
    0.24
    Activations Density 0.927%

    No Known Activations

    This feature has no known activations.