© 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. 141689
    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
    ongan
    -0.26
    lernen
    -0.26
    å¸ĤæķĻèĤ²å±Ģ
    -0.25
    ()._
    -0.25
     âĨĶ
    -0.24
    AVAILABLE
    -0.23
    å¾ĢåIJİ
    -0.23
    CALE
    -0.23
     triple
    -0.23
    SearchTree
    -0.23
    POSITIVE LOGITS
    å¢ŀé«ĺ
    0.29
    deo
    0.28
    大æĸ¹
    0.28
    gear
    0.26
    oe
    0.26
    æįı
    0.25
    èĵĩ
    0.25
    gars
    0.25
     cer
    0.25
     lv
    0.25
    Activations Density 7.632%

    No Known Activations

    This feature has no known activations.