© 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. 89961
    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
    Tac
    -0.29
     Merkel
    -0.28
    zan
    -0.28
    士
    -0.27
    Ham
    -0.26
    gist
    -0.26
    举
    -0.26
     presup
    -0.25
    ham
    -0.25
    pac
    -0.25
    POSITIVE LOGITS
    被æ·ĺæ±°
    0.27
     metic
    0.26
    ä¸įåIJĮç¨ĭ度
    0.26
     Que
    0.25
    )<<
    0.24
    ará
    0.24
     rightly
    0.24
    cxx
    0.24
     seq
    0.23
    ANEL
    0.23
    Activations Density 0.003%

    No Known Activations

    This feature has no known activations.