© 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. 4-TRANSCODER-HP
    7. 316
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_4.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.4.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¶Ĭ
    -0.32
    ette
    -0.26
    auss
    -0.26
    æ´ŀ
    -0.25
    å¾Ī好çļĦ
    -0.24
    BREAK
    -0.24
     start
    -0.24
    åįĹæŀģ
    -0.23
    é»Ķ
    -0.23
     Harvard
    -0.23
    POSITIVE LOGITS
    å¦ĵ
    0.28
     //'
    0.27
    çľ¼éĥ¨
    0.26
    æĬ¬èµ·å¤´
    0.26
    PIO
    0.26
    æĹłè¾ľ
    0.26
    quirer
    0.25
     ']
    0.25
    ascus
    0.25
     SqlConnection
    0.24
    Activations Density 0.024%

    No Known Activations

    This feature has no known activations.