© 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. 89945
    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
    è¿ĩåİ»çļĦ
    -0.29
     feelings
    -0.26
    alık
    -0.24
    Drupal
    -0.23
     rec
    -0.23
     BLE
    -0.23
    æĥħ趣
    -0.23
    identify
    -0.23
    åħ¥èģĮ
    -0.23
     perpetual
    -0.22
    POSITIVE LOGITS
     Patton
    0.28
    è¡«
    0.27
    ä¸įå¼Ģ
    0.26
     dop
    0.25
    é£İåIJ¹
    0.24
    庾
    0.24
    åIJĥ饱
    0.24
     suitable
    0.24
    çIJĨäºĭ
    0.24
    符åIJĪ
    0.24
    Activations Density 5.447%

    No Known Activations

    This feature has no known activations.