© 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. 96870
    Prev
    Next
    INDEX
    Explanations

    negative situations

    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
     '((
    -0.25
     Lives
    -0.25
     letter
    -0.25
    管çIJĨå·¥ä½ľ
    -0.24
     ITEMS
    -0.24
     Inn
    -0.24
     Ipsum
    -0.24
    rement
    -0.23
    etten
    -0.23
    EMENT
    -0.23
    POSITIVE LOGITS
     crisis
    0.37
     crises
    0.35
     shocks
    0.35
     unfavorable
    0.34
     circumstances
    0.32
     crashes
    0.31
     crashing
    0.31
     shock
    0.30
     fluctuations
    0.29
     disruptions
    0.29
    Activations Density 0.885%

    No Known Activations