© 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. 88324
    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
    Negative Logits
    带æĿ¥æĽ´å¤ļ
    -0.26
    аниÑĨ
    -0.25
    [++
    -0.25
    è¿ĺåİŁ
    -0.25
     Brig
    -0.25
    achers
    -0.24
    奥æŀĹåĮ¹
    -0.24
    个交æĺĵ
    -0.24
    Royal
    -0.23
     log
    -0.23
    POSITIVE LOGITS
     :-↵
    0.28
    coli
    0.28
    edad
    0.27
     Machines
    0.25
    ulos
    0.24
    寧
    0.24
    _TypeInfo
    0.24
    aria
    0.24
    å®ģ
    0.24
     Latitude
    0.23
    Activations Density 4.377%

    No Known Activations

    This feature has no known activations.