© 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. 107372
    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
    æŃĮåĶ±
    -0.24
    è§Ħå®ļçļĦ
    -0.24
    oron
    -0.24
    lage
    -0.24
    å¢ĥ
    -0.24
    -Mar
    -0.24
    fadeOut
    -0.23
    å·²ä¹ħçļĦ
    -0.23
     figured
    -0.23
     }}</
    -0.23
    POSITIVE LOGITS
    æ±ł
    0.28
     пÑĢоÑģ
    0.25
     SIDE
    0.24
    ä»»æľŁ
    0.24
    æĬ¥è¡¨
    0.24
    аÑĤÑĥÑĢ
    0.24
    пÑĢоÑģ
    0.23
    åĵİ
    0.23
    .inc
    0.23
     Assert
    0.23
    Activations Density 4.982%

    No Known Activations

    This feature has no known activations.