© 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. 20-TRANSCODER-HP
    7. 62804
    Prev
    Next
    INDEX
    Explanations

    omega

    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
    Negative Logits
    (rep
    -0.26
     overhaul
    -0.26
    åĬ¨æľº
    -0.26
     Guarantee
    -0.25
    anje
    -0.25
     motivated
    -0.25
    ilogy
    -0.25
    ação
    -0.25
    petition
    -0.24
    emption
    -0.24
    POSITIVE LOGITS
    åĪ°æŶåĢĻ
    0.26
    wis
    0.25
    è¡ĮåĪĹ
    0.23
    åįıä¼ļä¼ļåijĺ
    0.23
     wisdom
    0.23
    izedName
    0.23
    çĶ»åį·
    0.22
     tar
    0.22
    COPY
    0.22
    manifest
    0.22
    Activations Density 4.226%

    No Known Activations