© 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. 141601
    Prev
    Next
    INDEX
    Explanations

    Iran

    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
    agara
    -0.31
    vez
    -0.28
    éªĬ
    -0.27
    ackers
    -0.26
    ä»ĭ
    -0.26
    ème
    -0.25
    aign
    -0.24
    à¹Ħà¸Ĥ
    -0.24
    è´»
    -0.24
    ÃĵN
    -0.23
    POSITIVE LOGITS
    åĸĿèĮ¶
    0.26
    ets
    0.25
    詹å§Ĩ
    0.25
    è¿Ļåıª
    0.24
    æľĢ好
    0.24
    ä¸įèĪį
    0.24
    Coal
    0.23
    elastic
    0.23
    ewise
    0.23
    mvc
    0.23
    Activations Density 3.984%

    No Known Activations