© 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. 108298
    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
     Objects
    -0.32
     xét
    -0.26
    ä¿¡æģ¯åħ¬å¼Ģ
    -0.25
    ä¾Ŀæ³ķ
    -0.24
     Presents
    -0.24
    etus
    -0.23
    讽
    -0.23
     komen
    -0.23
    irror
    -0.23
    .setScene
    -0.23
    POSITIVE LOGITS
    .fm
    0.27
    inge
    0.26
    ijľ
    0.26
     Lomb
    0.25
    LETTE
    0.25
     Wat
    0.23
    (Mod
    0.23
    g
    0.23
    èĬĤ
    0.23
    -zA
    0.23
    Activations Density 46.780%

    No Known Activations

    This feature has no known activations.