© 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. 141346
    Prev
    Next
    INDEX
    Explanations

    Introducing concepts/possibilities

    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
    æģ£
    -0.31
    å¾Ĺä¸įåĪ°
    -0.29
    è¿ijè·Ŀ离
    -0.28
    лон
    -0.27
    æ²½
    -0.27
    illon
    -0.27
    unts
    -0.26
     Sporting
    -0.26
    æ£Ģæµĭ
    -0.26
     rec
    -0.25
    POSITIVE LOGITS
    edis
    0.31
    çİ°æľīçļĦ
    0.28
    çı©
    0.26
     sts
    0.25
    åħ¶ä»ĸçļĦ
    0.25
    zew
    0.24
    yre
    0.24
    sts
    0.24
    çĺª
    0.24
     Ru
    0.23
    Activations Density 15.305%

    No Known Activations