© 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. 141772
    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
    otre
    -0.26
    owitz
    -0.24
    ******/↵
    -0.24
    .FileWriter
    -0.24
    oly
    -0.24
    .sax
    -0.24
    recio
    -0.23
    åĽ¾ä¹¦
    -0.23
     tert
    -0.23
     bais
    -0.23
    POSITIVE LOGITS
    Agency
    0.26
     bodily
    0.26
    ESIS
    0.25
    æĮĩåIJij
    0.25
    åIJĪãĤıãģĽ
    0.24
     matrimon
    0.24
    æĺ
    0.24
    _resolve
    0.23
    ppard
    0.23
    (sl
    0.23
    Activations Density 0.209%

    No Known Activations

    This feature has no known activations.