© 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. 6348
    Prev
    Next
    INDEX
    Explanations

    Code/Markup

    np_max-act · gemini-2.0-flash
    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
     realistic
    -0.25
    	http
    -0.24
     flair
    -0.24
    ières
    -0.24
    tal
    -0.24
     dresser
    -0.24
    explicit
    -0.23
    AndServe
    -0.23
     complicated
    -0.23
     compart
    -0.23
    POSITIVE LOGITS
    oth
    0.29
    odal
    0.28
    èĿĩ
    0.25
    æĸ¹ä½į
    0.24
    åĭ¿
    0.23
     Oz
    0.23
    éĵµ
    0.23
    æIJį
    0.23
    åĨ·
    0.23
    á»ĵ
    0.23
    Activations Density 0.031%

    No Known Activations