© 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. 62640
    Prev
    Next
    INDEX
    Explanations

    less

    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
     subscribe
    -0.25
    straction
    -0.25
     Technique
    -0.25
    isoft
    -0.24
    æĽ´éĩįè¦ģçļĦ
    -0.23
     typealias
    -0.23
    letics
    -0.23
     credibility
    -0.23
     Went
    -0.23
    +=(
    -0.23
    POSITIVE LOGITS
     flare
    0.29
    .Reverse
    0.26
     flank
    0.24
    æĪIJç«ĭäºİ
    0.24
     Reverse
    0.24
    [x
    0.24
    Reverse
    0.24
    æľªæĽ¾
    0.23
    æ»ķ
    0.23
     du
    0.23
    Activations Density 16.224%

    No Known Activations