© 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. 56852
    Prev
    Next
    INDEX
    Explanations

    Abstract societal concepts

    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
    ç²īå°ĺ
    -0.27
    ingle
    -0.27
    è¦ģçĤ¹
    -0.26
    éĩįåŀĭ
    -0.26
     Tet
    -0.24
    缮ãģ®
    -0.24
    模å¼ı
    -0.24
    istant
    -0.24
    .@
    -0.24
    便
    -0.23
    POSITIVE LOGITS
     nationalism
    0.39
     friendship
    0.36
     conflict
    0.35
     immigration
    0.33
     racism
    0.33
     captivity
    0.32
     patriotism
    0.32
     morality
    0.32
     ambition
    0.31
     treason
    0.31
    Activations Density 0.004%

    No Known Activations