© 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. 18-TRANSCODER-HP
    7. 88483
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ñe
    -0.24
    æ³ģ
    -0.24
    è°Īèµ·
    -0.24
     <![
    -0.23
    åĬŀ好
    -0.23
     mary
    -0.23
     Shield
    -0.23
    çħ§æł·
    -0.23
    oger
    -0.23
    çĤ¬
    -0.23
    POSITIVE LOGITS
    �t
    0.28
    æĦŁè§ī
    0.26
    æĭĽ
    0.24
    uls
    0.24
    �
    0.24
    pawn
    0.24
    è¯Ń
    0.24
    archical
    0.23
     acceler
    0.23
    人æ°Ķ
    0.23
    Activations Density 3.285%

    No Known Activations

    This feature has no known activations.