© 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. 141829
    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
     fact
    -0.28
    ifest
    -0.27
     resumes
    -0.26
     Fact
    -0.25
    ersive
    -0.25
    éĹ
    -0.24
     activity
    -0.24
    ActivityCreated
    -0.24
    æľĢåIJİä¸Ģ个
    -0.24
    ivement
    -0.23
    POSITIVE LOGITS
    ügen
    0.25
    antha
    0.25
     trouble
    0.24
    åŀĽ
    0.23
    åIJ®
    0.23
    orning
    0.23
    讲æķħäºĭ
    0.23
    åħ¨çIJĥç»ıæµİ
    0.23
    讲课
    0.23
     zg
    0.23
    Activations Density 5.535%

    No Known Activations

    This feature has no known activations.