© 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. 129772
    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
    Ã¼ÃŁ
    -0.26
    缺
    -0.25
    ä¸Ģ对ä¸Ģ
    -0.25
    .mj
    -0.24
    iterated
    -0.24
    ARRIER
    -0.24
    ographies
    -0.24
    getOption
    -0.23
    atatype
    -0.23
    inds
    -0.23
    POSITIVE LOGITS
     quil
    0.27
    ä¸ĭæĸ¹
    0.26
    ä»ĸ们çļĦ
    0.26
    ilion
    0.25
    ä½Ĩä»ĸ们
    0.25
    è¿Ļ家åħ¬åı¸
    0.25
    :http
    0.25
     Flooring
    0.24
    è¿Ļä¸ªåľ°æĸ¹
    0.24
     :(
    0.24
    Activations Density 0.126%

    No Known Activations

    This feature has no known activations.