© 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. 90280
    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
    DataContext
    -0.30
    icum
    -0.26
    edom
    -0.25
    adel
    -0.24
    ader
    -0.24
    erea
    -0.24
     guiding
    -0.24
    ë¥ĺ
    -0.24
    allen
    -0.24
    éĢĨ
    -0.24
    POSITIVE LOGITS
    KHR
    0.29
     technically
    0.28
     configFile
    0.27
     conv
    0.26
    æĿ¥ä¸įåıĬ
    0.26
    æľīå¤ļ
    0.25
    ète
    0.25
    -blind
    0.24
    _exempt
    0.24
    ç»Ī身
    0.24
    Activations Density 0.269%

    No Known Activations

    This feature has no known activations.