© 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. 142620
    Prev
    Next
    INDEX
    Explanations

    that if

    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
    essim
    -0.28
    åĴĮä»ĸçļĦ
    -0.27
    ously
    -0.27
    æŃī
    -0.26
    å¿ĥ仪
    -0.26
    ç¾İ好
    -0.25
    使å¾Ĺ
    -0.25
    able
    -0.25
    她说
    -0.25
    页
    -0.24
    POSITIVE LOGITS
    acha
    0.29
     poste
    0.25
     Combined
    0.24
    åĨįå¤ļ
    0.24
     achieved
    0.23
    æĶ¯
    0.23
     nothing
    0.23
     recal
    0.23
    {č↵
    0.23
     combined
    0.23
    Activations Density 19.813%

    No Known Activations