© 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. 30-TRANSCODER-HP
    7. 95742
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    obot
    -0.29
    æµĬ
    -0.27
     @{↵
    -0.26
    åģļè¿ĩ
    -0.25
    á»ijc
    -0.25
    richt
    -0.24
    meric
    -0.24
    缮çļĦ
    -0.24
    åijĬ
    -0.23
    æ¹ĸåĮº
    -0.23
    POSITIVE LOGITS
    SORT
    0.28
    iks
    0.25
    é³Į
    0.25
    oldem
    0.25
    ä¸ĢæĿ¡é¾Ļ
    0.24
     memcmp
    0.24
     Troll
    0.24
    apphire
    0.24
     Daw
    0.24
    çĪ±ä¸Ĭ
    0.24
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.