© 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. 4837
    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
    ypy
    -0.30
    vac
    -0.29
    pé
    -0.27
    ÑĭваÑĤÑĮ
    -0.27
    çŁ¥æĥħ
    -0.26
    ä¸ĵ项è¡ĮåĬ¨
    -0.26
    è¯Ŀ
    -0.26
    å¤ĸå¥Ĺ
    -0.24
    丢失
    -0.24
    åģľå·¥
    -0.23
    POSITIVE LOGITS
    .getUrl
    0.27
    åįĩ
    0.26
     Din
    0.26
    åĿļ
    0.25
    éį
    0.25
    æłĩåĩĨ
    0.23
    æµ´
    0.23
    igm
    0.23
    alk
    0.22
    orks
    0.22
    Activations Density 1.046%

    No Known Activations

    This feature has no known activations.