© 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. 20-TRANSCODER-HP
    7. 130548
    Prev
    Next
    INDEX
    Explanations

    Coronavirus (COVID-19)

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    丰满
    -0.29
    æīij
    -0.28
    setDisplay
    -0.28
    ç®Ń
    -0.27
    bone
    -0.27
    麻
    -0.26
    ibia
    -0.26
     abbrev
    -0.25
    adj
    -0.25
    opt
    -0.24
    POSITIVE LOGITS
    çıŃ级
    0.27
    &_
    0.27
     amongst
    0.26
     doubling
    0.25
    fter
    0.25
    éĺ»åĬĽ
    0.25
    çļĦåİĭåĬĽ
    0.25
    ä¸ĵ注
    0.24
    ä½İ温
    0.24
    INGTON
    0.24
    Activations Density 2.671%

    No Known Activations