© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 163111
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .promise
    -0.27
    aylight
    -0.27
    ITO
    -0.26
    表çݰ为
    -0.25
    IG
    -0.24
     digital
    -0.24
    ä¾Ľç»Ļ
    -0.24
    lage
    -0.24
    aise
    -0.24
     Case
    -0.23
    POSITIVE LOGITS
     curs
    0.28
    带ä¸Ĭ
    0.27
    inters
    0.26
    æķıæĦŁ
    0.26
     Chambers
    0.26
    ä¸ŃåĽ½æĸĩåĮĸ
    0.26
     Weiner
    0.25
     Conserv
    0.25
    è¢ĸ
    0.25
    件
    0.24
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.