© 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. 6246
    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
    atar
    -0.26
    åįı
    -0.26
    æĭİ
    -0.25
    çļĦèĥ½åĬĽ
    -0.25
    åIJ¸
    -0.24
    åħ¨èº«
    -0.24
    uda
    -0.24
    sexual
    -0.24
    å®ł
    -0.23
    chia
    -0.23
    POSITIVE LOGITS
    è±Ĩ
    0.29
    onds
    0.26
    大éĻ¸
    0.26
    éĿŀè¦ģ
    0.25
    ynos
    0.25
    _pot
    0.24
    ä¸Ŀä¸Ŀ
    0.23
    łģ
    0.23
    æ·¦
    0.23
    ables
    0.23
    Activations Density 0.034%

    No Known Activations

    This feature has no known activations.