© 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. 108290
    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
    impl
    -0.26
    é©»
    -0.25
    PBS
    -0.25
    kers
    -0.24
    ocs
    -0.24
     CCS
    -0.24
    coded
    -0.24
     unb
    -0.23
    å¸Ī
    -0.23
    oad
    -0.23
    POSITIVE LOGITS
    èģĶç³»æĸ¹å¼ı
    0.25
    çĶ¨è½¦
    0.25
    UNCTION
    0.25
    Sand
    0.25
     nests
    0.25
     awaits
    0.24
    orman
    0.24
     sedan
    0.24
    sie
    0.24
    (bot
    0.24
    Activations Density 71.690%

    No Known Activations

    This feature has no known activations.