© 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. 107682
    Prev
    Next
    INDEX
    Explanations

    cause and effect

    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
    uate
    -0.29
    æŃ¤åŁºç¡Ģä¸Ĭ
    -0.28
    oplan
    -0.28
    乡
    -0.26
    burgh
    -0.26
    uard
    -0.26
    ondon
    -0.26
    /spec
    -0.25
    zelf
    -0.25
    wise
    -0.25
    POSITIVE LOGITS
    èİ«
    0.28
    åįģå¹´åīį
    0.26
    å°Ĩèĩªå·±çļĦ
    0.25
    æİĪ
    0.25
    å¹´åĨħ
    0.25
    trie
    0.24
     Association
    0.24
    æĹĮ
    0.24
    try
    0.24
    æĭľ
    0.24
    Activations Density 13.454%

    No Known Activations