© 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. 107430
    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
    æľŁæľĽ
    -0.31
    eph
    -0.27
     Co
    -0.27
    _lua
    -0.27
    åıĪè¦ģ
    -0.26
    ä¹Łå¸ĮæľĽ
    -0.26
     Charleston
    -0.25
    -between
    -0.25
     rounds
    -0.24
     memcpy
    -0.23
    POSITIVE LOGITS
    ousel
    0.32
     packs
    0.30
    obel
    0.28
    edException
    0.26
    鸳
    0.26
    è¾ĸåĮºåĨħ
    0.25
    è°±
    0.25
    rim
    0.25
    ibox
    0.25
    abox
    0.24
    Activations Density 22.029%

    No Known Activations

    This feature has no known activations.