© 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. 88097
    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
     fet
    -0.27
    æĬ¥
    -0.26
     Euras
    -0.26
    æĬ¥å¤į
    -0.25
    EDIA
    -0.25
     meer
    -0.25
     involving
    -0.25
    UGC
    -0.24
    -letter
    -0.24
    illum
    -0.23
    POSITIVE LOGITS
    åIJ¬å¾Ĺ
    0.30
     padd
    0.26
     Inside
    0.25
     onStop
    0.25
     inside
    0.25
     suites
    0.24
    æ§Ľ
    0.24
     Verde
    0.24
    zens
    0.24
    iske
    0.24
    Activations Density 39.617%

    No Known Activations

    This feature has no known activations.