© 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. 63570
    Prev
    Next
    INDEX
    Explanations

    Research questions and actions

    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
    asin
    -0.29
    åħ¨è¦ĨçĽĸ
    -0.27
    ga
    -0.26
    æ¸ħåįİ
    -0.24
     evid
    -0.23
    mesh
    -0.23
     hashCode
    -0.23
     flexible
    -0.23
     BOTH
    -0.23
     WHATSOEVER
    -0.23
    POSITIVE LOGITS
    .serializer
    0.27
    -plugins
    0.25
    wick
    0.25
     kü
    0.25
     intentionally
    0.25
    ÑģÑģ
    0.25
    请çĤ¹åĩ»
    0.25
    ../../../../
    0.24
    -url
    0.24
    Lit
    0.24
    Activations Density 19.829%

    No Known Activations