© 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. 63420
    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
    è¦ģåѦä¼ļ
    -0.33
    ä¸ĢæĿ¡é¾Ļ
    -0.30
    è¦ģæľī
    -0.25
    èĥ½å¾ĹåĪ°
    -0.25
    exo
    -0.25
    slideUp
    -0.25
    emento
    -0.25
    åĪĨæīĭ
    -0.25
    èĴIJ
    -0.25
    åIJĦè¡Į
    -0.24
    POSITIVE LOGITS
    pak
    0.28
     town
    0.27
     Pak
    0.26
    åij¨
    0.26
    pkg
    0.25
     tÆ°á»Ŀng
    0.25
    çĩķ
    0.25
     Networking
    0.25
     Indy
    0.24
     Add
    0.24
    Activations Density 1.729%

    No Known Activations

    This feature has no known activations.