© 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. 141253
    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
    åħļçļĦ建设
    -0.28
    abcdefgh
    -0.26
    sessions
    -0.25
    sports
    -0.25
    éĩĩ访æŶ
    -0.25
    åı²
    -0.24
    olicies
    -0.24
    èħł
    -0.24
    readcrumb
    -0.24
    overe
    -0.24
    POSITIVE LOGITS
     pong
    0.28
     slippery
    0.25
    **)&
    0.25
    åıĮæĸ¹
    0.25
    aska
    0.25
    è´¡
    0.25
    åĨ³ä¸į
    0.25
    ç»Ŀä¸į
    0.24
    /MIT
    0.24
     states
    0.24
    Activations Density 7.905%

    No Known Activations

    This feature has no known activations.