© 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. 141607
    Prev
    Next
    INDEX
    Explanations

    Code and copyright notices

    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
    æŃ
    -0.28
    ette
    -0.26
    æŃ¢
    -0.25
    αι
    -0.24
     leuk
    -0.24
    <fieldset
    -0.23
    ogy
    -0.23
    .constructor
    -0.23
    xmm
    -0.23
    第äºĮèĬĤ
    -0.23
    POSITIVE LOGITS
     covid
    0.32
     Covid
    0.31
    æĸ°åĨłèĤºçĤİ
    0.29
     https
    0.28
    纾
    0.28
    åĪĿå¿ĥ
    0.27
    iol
    0.27
     COVID
    0.25
    COVID
    0.25
    =https
    0.24
    Activations Density 7.242%

    No Known Activations