© 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. 4-TRANSCODER-HP
    7. 133
    Prev
    Next
    INDEX
    Explanations

    trees and wood

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_4.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.4.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    illi
    -0.30
    æīĢå±ŀ
    -0.28
    aget
    -0.26
    æĪijæĥ³
    -0.26
    atsapp
    -0.25
     Ago
    -0.25
    é²
    -0.25
    atur
    -0.25
    å°Ķ
    -0.24
    èµŀæĪIJ
    -0.24
    POSITIVE LOGITS
    enh
    0.26
    ãĥ¯ãĥ¼ãĤ¯
    0.25
    елÑı
    0.25
    çļĦä¿¡ä»»
    0.25
     lung
    0.24
    ä¸Ģå¾ĭ
    0.24
    ç»Ļä»ĸ们
    0.24
     hÆ°Æ¡ng
    0.24
    .once
    0.23
    墩
    0.23
    Activations Density 0.019%

    No Known Activations