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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 7460
    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
    ptune
    -0.30
    missions
    -0.25
    éĴī
    -0.25
    odox
    -0.25
    æķ´æĶ¹æݪæĸ½
    -0.25
    æ¯ıä¸Ģ次
    -0.24
    带ç»Ļ
    -0.24
     land
    -0.24
    æī«ä¸Ģæī«
    -0.24
     [...]↵↵
    -0.24
    POSITIVE LOGITS
    tons
    0.28
    atin
    0.25
    æĽ´åĥıæĺ¯
    0.25
    åıªä¸įè¿ĩæĺ¯
    0.25
    çģ«è½¦ç«Ļ
    0.24
    ystore
    0.24
     Stadium
    0.24
     TInt
    0.24
    èļĮ
    0.24
    æģ¤
    0.23
    Activations Density 2.318%

    No Known Activations

    This feature has no known activations.