© 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. 141002
    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
    ales
    -0.28
    足迹
    -0.26
    è¿Ļä¸įæĺ¯
    -0.26
    ź
    -0.25
    Features
    -0.24
    -turn
    -0.24
    Respond
    -0.24
    Originally
    -0.23
     Exposure
    -0.23
    ome
    -0.23
    POSITIVE LOGITS
    é¹Ĥ
    0.33
    uspend
    0.25
    æĹ¥è®¯
    0.24
    SEMB
    0.24
    çĪĨçĤ¸
    0.24
    ẫn
    0.23
    ÑĮеÑĢ
    0.23
    grep
    0.23
     crossorigin
    0.23
    instr
    0.23
    Activations Density 14.935%

    No Known Activations

    This feature has no known activations.