© 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. 62970
    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
    grave
    -0.28
    åģľ
    -0.27
    éĶŃ
    -0.27
    ugi
    -0.26
    uga
    -0.26
    è¡·
    -0.26
     Grave
    -0.25
    eba
    -0.25
    WD
    -0.25
    lek
    -0.25
    POSITIVE LOGITS
    ä¸Ģåı·
    0.26
    ä¸įåħ¬å¹³
    0.25
    ç»Ļä½łä»¬
    0.24
     åĪ
    0.24
    æıIJèµ·
    0.24
    ì»
    0.23
     referrals
    0.23
     subsequent
    0.23
     Science
    0.23
    loyd
    0.23
    Activations Density 4.900%

    No Known Activations

    This feature has no known activations.