© 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. 90321
    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
    å»Ľ
    -0.29
    ocations
    -0.28
    asking
    -0.26
    -turn
    -0.26
    oni
    -0.26
     trùng
    -0.25
    Infrastructure
    -0.24
    istance
    -0.24
     distance
    -0.23
    essential
    -0.23
    POSITIVE LOGITS
     sourceMappingURL
    0.29
    è´¨éĩı管çIJĨ
    0.26
     Waters
    0.26
    æ¯ĭ
    0.25
    inium
    0.24
    \/\/
    0.24
     priorit
    0.24
     startActivityForResult
    0.24
    urger
    0.23
    å©¿
    0.23
    Activations Density 0.010%

    No Known Activations

    This feature has no known activations.