© 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. 31-TRANSCODER-HP
    7. 17841
    Prev
    Next
    INDEX
    Explanations

    oil and gas industry

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     commun
    -0.26
    å±ķåĵģ
    -0.25
    ACY
    -0.24
     COMPUTER
    -0.24
    åħ¨æĿij
    -0.24
    fruit
    -0.24
    chemist
    -0.24
    æŀľ
    -0.24
     vict
    -0.23
    å¯Ĩ度
    -0.23
    POSITIVE LOGITS
     pipeline
    0.34
     pipelines
    0.33
     drill
    0.32
    æĮĸ
    0.31
     rigs
    0.30
     refining
    0.28
     reserve
    0.27
     ÑĤÑĢÑĥб
    0.27
    éĴ»
    0.26
    桶
    0.26
    Activations Density 1.195%

    No Known Activations