© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 31-TRANSCODER-HP
    7. 19092
    Prev
    Next
    INDEX
    Explanations

    Related to "live"

    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
    Not in Any Lists

    No Comments

    Negative Logits
    æĵĺ
    -0.26
    ken
    -0.25
    WithPath
    -0.24
    åŁł
    -0.24
    boys
    -0.24
    omers
    -0.23
    åĬĪ
    -0.23
     Coming
    -0.23
    heet
    -0.23
    ulan
    -0.23
    POSITIVE LOGITS
    æ´»
    1.37
     live
    1.26
    live
    1.12
     lived
    1.06
     Live
    1.04
     living
    1.02
    Live
    1.00
    -live
    0.97
    _live
    0.93
    living
    0.90
    Activations Density 33.603%

    No Known Activations