© 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. 27-TRANSCODER-HP
    7. 8534
    Prev
    Next
    INDEX
    Explanations

    culture

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è¯ģåĪ¸æĬķèµĦ
    -0.29
     Dob
    -0.26
    Exceptions
    -0.25
    sit
    -0.25
    üstü
    -0.24
    rys
    -0.24
     Primitive
    -0.24
    GED
    -0.24
    æĸ°éĹ»åıijå¸ĥ
    -0.24
    owers
    -0.24
    POSITIVE LOGITS
     culture
    1.10
     Culture
    0.94
    culture
    0.87
     cultures
    0.86
    æĸĩåĮĸ
    0.80
    æĸĩåĮĸåĴĮ
    0.80
    Culture
    0.79
    æĸĩåĮĸçļĦ
    0.76
     cultura
    0.75
    ä¼ģä¸ļæĸĩåĮĸ
    0.71
    Activations Density 0.005%

    No Known Activations