© 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. 63858
    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
     syn
    -0.28
    æĮīæij©
    -0.26
     ngu
    -0.25
     stag
    -0.24
    ither
    -0.24
    ÑĥÑĢÑģ
    -0.24
    é¢ijç¹ģ
    -0.24
    жив
    -0.24
    REQUIRED
    -0.24
    arnation
    -0.24
    POSITIVE LOGITS
    ascript
    0.27
    åijĬ
    0.26
    ç²¾ç¥ŀ
    0.26
    åıij表äºĨ
    0.25
    KeyId
    0.25
     há»Ļ
    0.25
    åıĺæĪIJ
    0.25
     indirect
    0.24
    èĢģçĪ¸
    0.24
     indirectly
    0.24
    Activations Density 0.221%

    No Known Activations

    This feature has no known activations.