© 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. 88193
    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
    æľĪæľ«
    -0.30
    getManager
    -0.29
    æ¯ı人
    -0.27
    å¹´æľ«
    -0.25
    acak
    -0.25
    gaard
    -0.25
     glyc
    -0.25
    å¾Ĺ天
    -0.24
    getExtension
    -0.24
    leston
    -0.23
    POSITIVE LOGITS
    污
    0.28
    å°±èĥ½
    0.27
    lus
    0.27
    otte
    0.27
    аÑĩ
    0.25
    央
    0.25
    ulum
    0.24
    iences
    0.23
    akt
    0.23
    å°±æĪIJäºĨ
    0.23
    Activations Density 5.799%

    No Known Activations

    This feature has no known activations.