© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 5944
    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
    éļĶ
    -0.28
    berries
    -0.27
     movers
    -0.27
    ber
    -0.26
    ä¸įåİ»
    -0.24
    éĿĴ
    -0.24
    underline
    -0.24
    bern
    -0.24
    ç²¾
    -0.24
    æłijç«ĭ
    -0.24
    POSITIVE LOGITS
     Tit
    0.28
    æĺ¯ä¸Ģ款
    0.28
    è¿Ļ款
    0.28
     tit
    0.27
    ensi
    0.27
     titre
    0.27
    éĴį
    0.26
    ä¸ĢåľĪ
    0.26
    tit
    0.26
    Tit
    0.26
    Activations Density 0.060%

    No Known Activations

    This feature has no known activations.