© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 129606
    Prev
    Next
    INDEX
    Explanations

    Code and technical specifications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    roulette
    -0.28
    bee
    -0.25
     brown
    -0.25
    éĽ¯
    -0.24
    åĩºäºİ
    -0.24
    popular
    -0.24
    å±Ģéķ¿
    -0.24
    _tests
    -0.24
    -tests
    -0.23
    umb
    -0.23
    POSITIVE LOGITS
    çļĦæķ´ä½ĵ
    0.28
     Pron
    0.27
     chá»ĭu
    0.27
    å¿įåıĹ
    0.26
     Swim
    0.25
    æĬĬæı¡
    0.25
    æĥķ
    0.25
    æĢ»æĬķèµĦ
    0.25
    èįł
    0.25
    çļĦæĸ¹åIJij
    0.25
    Activations Density 1.608%

    No Known Activations