© 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. 30-TRANSCODER-HP
    7. 96998
    Prev
    Next
    INDEX
    Explanations

    environmental

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    enet
    -0.30
    RIA
    -0.28
    QT
    -0.26
    åħīçĶµ
    -0.26
    åĨ·æ°´
    -0.25
    溶解
    -0.25
    ä½İ温
    -0.24
     Bair
    -0.24
     diss
    -0.24
     Diss
    -0.24
    POSITIVE LOGITS
     environmental
    0.37
     expos
    0.35
     exposure
    0.33
    æĽĿ
    0.31
     ep
    0.30
    æļ´éľ²
    0.30
     env
    0.29
    .env
    0.28
    çݯå¢ĥ
    0.28
     Environmental
    0.28
    Activations Density 0.907%

    No Known Activations