© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 142054
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ospace
    -0.28
    orp
    -0.27
    ç§ĺ
    -0.26
    /gpl
    -0.26
    .gstatic
    -0.25
     Ange
    -0.25
     cap
    -0.24
    -fw
    -0.24
    åĪ¤
    -0.24
    á»Ŀi
    -0.24
    POSITIVE LOGITS
     ÑģоÑħ
    0.27
     pallet
    0.26
     ApplicationRecord
    0.25
    åŁºè¾ħ
    0.24
    itat
    0.24
    海峡
    0.24
    æķ°éĩı
    0.23
     UICollectionView
    0.23
     compreh
    0.23
    atted
    0.23
    Activations Density 5.454%

    No Known Activations

    This feature has no known activations.