© 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. 63314
    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
    iola
    -0.27
    èĬ¯
    -0.26
    culate
    -0.25
    å®°
    -0.25
     ÐŁÐ°
    -0.24
    locate
    -0.24
    iationException
    -0.24
    ytic
    -0.23
    .preview
    -0.23
    bral
    -0.23
    POSITIVE LOGITS
    æĬķæĶ¾
    0.28
    åĮ»å¸Ī
    0.27
     Shr
    0.27
    é«ĺä½į
    0.25
    ç¼Ļ
    0.24
    .fd
    0.24
    unts
    0.24
     dropping
    0.24
    带走
    0.23
    à¸ķร
    0.23
    Activations Density 42.637%

    No Known Activations

    This feature has no known activations.