© 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. 107347
    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
    tridge
    -0.27
    astro
    -0.25
     Lot
    -0.25
    tractor
    -0.24
    imed
    -0.24
    ARTH
    -0.23
     lag
    -0.23
     closest
    -0.23
    åѦä½į
    -0.23
    emm
    -0.23
    POSITIVE LOGITS
    å¢ŀ
    0.27
    æłĩ
    0.27
    èĪįå¾Ĺ
    0.26
    å¼ĢåıijèĢħ
    0.25
    ä¸įåIJ«
    0.25
     Hey
    0.25
    讫
    0.24
    稼
    0.24
    禼
    0.23
    road
    0.23
    Activations Density 2.269%

    No Known Activations

    This feature has no known activations.