© 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. 4946
    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
    ends
    -0.29
     ende
    -0.28
    æĭ¼
    -0.27
    åĨį说
    -0.25
    ents
    -0.25
    én
    -0.25
    æĶ¶å®ĺ
    -0.25
    EN
    -0.25
    ä»£æĽ¿
    -0.25
     borderBottom
    -0.25
    POSITIVE LOGITS
    dio
    0.26
    åĩ¸æĺ¾
    0.26
     seize
    0.26
    :variables
    0.26
    asers
    0.25
     ribs
    0.24
    é¢Ĥ
    0.24
     sesame
    0.24
    edly
    0.24
     wipe
    0.24
    Activations Density 0.274%

    No Known Activations

    This feature has no known activations.