© 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. 163046
    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
     onboard
    -0.32
    æĹłåģ¿
    -0.29
    zend
    -0.25
    lei
    -0.25
    ounc
    -0.25
     kino
    -0.25
    Den
    -0.24
    orts
    -0.24
    æĶ¾è¿ĩ
    -0.24
    åŁºè°ĥ
    -0.24
    POSITIVE LOGITS
    ican
    0.27
    hoe
    0.26
    à¹Ĥล
    0.25
     mÃłn
    0.25
     chair
    0.25
     Pitt
    0.24
    ifiable
    0.24
    éĸĢ
    0.24
    对æѤ
    0.24
     Bill
    0.24
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.