© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 27-TRANSCODER-HP
    7. 9519
    Prev
    Next
    INDEX
    Explanations

    environmental sustainability

    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
    boa
    -0.26
    rov
    -0.25
     Unity
    -0.24
    纪å¾ĭ
    -0.24
    illez
    -0.24
    /content
    -0.23
     bian
    -0.23
    骧
    -0.23
    éĽªèĬ±
    -0.23
    íĤ·
    -0.23
    POSITIVE LOGITS
    çݯä¿Ŀ
    1.15
     environmentally
    1.02
     environmental
    0.98
     sustainability
    0.97
    çݯå¢ĥä¿ĿæĬ¤
    0.89
     eco
    0.89
     sustainable
    0.88
     Sustainability
    0.87
    绿èī²çݯä¿Ŀ
    0.84
    绿èī²
    0.83
    Activations Density 0.022%

    No Known Activations