© 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. 142232
    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
    mp
    -0.29
    mps
    -0.29
     L
    -0.28
    笼
    -0.27
    ено
    -0.27
    RS
    -0.27
     Coke
    -0.27
    èĥĮçĿĢ
    -0.26
     WH
    -0.26
    MP
    -0.25
    POSITIVE LOGITS
    æĹ¥è®¯
    0.33
    hare
    0.30
    eah
    0.28
    -Aug
    0.27
    ObjectContext
    0.26
     narration
    0.26
    貫
    0.26
    ijľ
    0.26
    ovie
    0.26
    æij¸ç´¢
    0.25
    Activations Density 3.509%

    No Known Activations

    This feature has no known activations.