© 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. 41947
    Prev
    Next
    INDEX
    Explanations

    main

    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
    éĻĤ
    -0.26
    毫ä¸įçĬ¹è±«
    -0.26
    uli
    -0.26
    á»ijt
    -0.26
     sack
    -0.25
    ÐĴидео
    -0.25
    éĴ©
    -0.25
    åĢĴ
    -0.25
    æѦè£ħ
    -0.24
    ç¾İ
    -0.24
    POSITIVE LOGITS
     main
    0.55
     Main
    0.41
     different
    0.38
    main
    0.38
    	main
    0.37
    MAIN
    0.36
    (main
    0.35
    Main
    0.35
     MAIN
    0.35
    .main
    0.34
    Activations Density 0.000%

    No Known Activations