© 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. 141224
    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
    èıģ
    -0.28
    åIJĮ
    -0.27
     conferred
    -0.27
    æĺ¾
    -0.27
     Infer
    -0.25
    ä¸įå¾Ĺå·²
    -0.24
    èĻı
    -0.24
    交æį¢
    -0.24
    è¯İ
    -0.24
    OPS
    -0.23
    POSITIVE LOGITS
    itez
    0.30
    åŃĹåı·
    0.26
    )<<
    0.25
    лÑİб
    0.25
     Recommend
    0.25
    wizard
    0.25
    arkan
    0.24
    uerdo
    0.24
     Rica
    0.24
     Plat
    0.24
    Activations Density 29.433%

    No Known Activations

    This feature has no known activations.