© 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. 107527
    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
    åħ¼
    -0.29
    åı¯è¡ĮæĢ§
    -0.27
     Pompe
    -0.26
    é£ŀ
    -0.26
    äºĨåIJĹ
    -0.26
    身躯
    -0.25
    èµ·é£ŀ
    -0.24
    Ot
    -0.24
    çļĦæĦıæĢĿ
    -0.24
     Brave
    -0.24
    POSITIVE LOGITS
    QRST
    0.29
    iere
    0.28
    mlin
    0.27
    满äºĨ
    0.26
    istring
    0.25
    inia
    0.25
    åĬŃ
    0.25
    ä¸Ģ个å¤ļ
    0.24
    æĪ¿éĹ´éĩĮ
    0.24
    finity
    0.24
    Activations Density 2.796%

    No Known Activations

    This feature has no known activations.