© 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. 64475
    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
    æļ®
    -0.29
    饵
    -0.26
    enco
    -0.25
     lique
    -0.25
    gett
    -0.23
    樵
    -0.23
    usher
    -0.23
    ROUGH
    -0.23
     liquor
    -0.23
     mol
    -0.23
    POSITIVE LOGITS
    èĽ©
    0.27
    agrams
    0.24
    -packages
    0.24
    gram
    0.24
    åĮºæĶ¿åºľ
    0.23
    sonian
    0.23
    cosystem
    0.23
    å·¥ä½ľæķĪçİĩ
    0.23
    èĥ¡åIJĮ
    0.22
     packages
    0.22
    Activations Density 20.573%

    No Known Activations

    This feature has no known activations.