© 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. 151166
    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
    æłĩé¢ĺ
    -0.26
    antics
    -0.25
    nect
    -0.24
    ant
    -0.24
    主ä¸ļ
    -0.24
     diz
    -0.23
    è¿Ļ个åIJįåŃĹ
    -0.23
    Ùģ
    -0.23
    TemplateName
    -0.23
    âĶ¤
    -0.23
    POSITIVE LOGITS
     Gecko
    0.22
    Ãītat
    0.22
    getApplication
    0.22
     retina
    0.22
     Gallup
    0.22
    acı
    0.22
     StraÃŁen
    0.22
     Autodesk
    0.21
     underside
    0.21
    æĻ¾
    0.21
    Activations Density 0.197%

    No Known Activations

    This feature has no known activations.