© 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. 32-TRANSCODER-HP
    7. 41644
    Prev
    Next
    INDEX
    Explanations

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     main
    -1.28
    main
    -1.20
    _main
    -0.99
    Main
    -0.99
     Main
    -0.97
    主
    -0.97
    .main
    -0.97
    	main
    -0.96
    -main
    -0.93
    (main
    -0.93
    POSITIVE LOGITS
    emode
    0.27
    LBL
    0.25
    ulators
    0.24
    ìĽIJ
    0.24
    erras
    0.24
    ,:,
    0.23
    æĶ¾æīĭ
    0.23
    çĬ·
    0.23
    çļĦç«ŀäºī
    0.23
     pard
    0.23
    Activations Density 0.012%

    No Known Activations