© 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. 19693
    Prev
    Next
    INDEX
    Explanations

    words related to "event"

    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
    ä»»ä½ķ
    -0.28
    annel
    -0.26
    éĺ´
    -0.25
     MPS
    -0.25
    bies
    -0.25
    ç»ĵ
    -0.24
    é£ĺ
    -0.24
     cris
    -0.24
     лÑİбого
    -0.23
    NY
    -0.23
    POSITIVE LOGITS
     eventual
    1.08
     eventually
    1.06
     Eventually
    0.79
    Eventually
    0.68
     event
    0.68
    event
    0.67
     ultimately
    0.60
     Event
    0.54
     EVENT
    0.51
    .event
    0.51
    Activations Density 2.128%

    No Known Activations