© 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. 107311
    Prev
    Next
    INDEX
    Explanations

    with

    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
    ä¸įä½ı
    -0.30
    <Boolean
    -0.28
     Boolean
    -0.26
    æĬĵ
    -0.26
    atalog
    -0.25
     pys
    -0.25
    variables
    -0.24
    boolean
    -0.24
    nez
    -0.24
    orts
    -0.24
    POSITIVE LOGITS
    åį°è±¡
    0.30
    笼
    0.28
    è¯Ŀ
    0.27
    诣
    0.27
    ä¼łç»Łäº§ä¸ļ
    0.27
    ä½İ声
    0.26
    erde
    0.26
    ]+'
    0.25
    åŁ½
    0.25
    rone
    0.25
    Activations Density 7.529%

    No Known Activations