© 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. 19-TRANSCODER-HP
    7. 4735
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    表彰
    -0.28
    ItemAt
    -0.27
    dle
    -0.26
    ecer
    -0.26
     favor
    -0.26
    /tos
    -0.26
    æ¯Ķäºļ
    -0.25
     favors
    -0.24
     favored
    -0.24
    favor
    -0.24
    POSITIVE LOGITS
    esen
    0.29
    antha
    0.27
    æĥij
    0.26
    åĸĦ
    0.25
    queeze
    0.25
     *</
    0.24
     hin
    0.24
    -scripts
    0.24
    *</
    0.24
     Thrones
    0.24
    Activations Density 1.892%

    No Known Activations

    This feature has no known activations.