© 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. 23-TRANSCODER-HP
    7. 23518
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    iques
    -0.28
    para
    -0.25
    è¥Ł
    -0.24
    å¾Ĺä½ı
    -0.24
    äºĨä¸Ģåı¥
    -0.24
    åĪ¶è®¢
    -0.24
     ÑĦон
    -0.23
    iper
    -0.23
    æł¼å°Ķ
    -0.23
    ientes
    -0.23
    POSITIVE LOGITS
    bons
    0.29
    addle
    0.27
    æĹłäºº
    0.26
    unting
    0.25
     multis
    0.24
    cratch
    0.24
     lunar
    0.24
    mons
    0.23
    utom
    0.23
    èİ«
    0.23
    Activations Density 0.008%

    No Known Activations

    This feature has no known activations.