© 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. 107848
    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
    ä¸įæĿ¥
    -0.32
    å·´å·´
    -0.28
    ansi
    -0.27
    subjects
    -0.26
    æ°ļ
    -0.26
    oire
    -0.26
    illary
    -0.25
    éĺ¼
    -0.25
    .subject
    -0.25
    æĶ¸
    -0.25
    POSITIVE LOGITS
     undone
    0.29
    -mail
    0.28
     pulumi
    0.25
     Estate
    0.24
     alone
    0.24
     dumping
    0.24
     dressed
    0.23
     вÑĭполнен
    0.23
    iomanip
    0.23
    鹤
    0.23
    Activations Density 4.601%

    No Known Activations

    This feature has no known activations.