© 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. 129931
    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
     elevate
    -0.29
    å¤ļæł·
    -0.25
    NAS
    -0.25
     inf
    -0.24
     preca
    -0.24
     Tale
    -0.24
     swift
    -0.24
    åįķä½į
    -0.24
     NAS
    -0.24
     precaution
    -0.24
    POSITIVE LOGITS
     Imports
    0.26
     comforts
    0.25
     Bs
    0.25
     mee
    0.23
     pins
    0.23
    encias
    0.23
     {}).
    0.23
    zia
    0.23
     clap
    0.23
    ä¸įæĺİ
    0.23
    Activations Density 42.527%

    No Known Activations

    This feature has no known activations.