© 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. 130909
    Prev
    Next
    INDEX
    Explanations

    announcements

    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
     readiness
    -0.29
    æľ¬ç½ij
    -0.28
    è¯ļæĦı
    -0.26
    äºĨåIJĹ
    -0.26
    åĮ»ç§ij
    -0.26
    èĬ¥
    -0.26
    endale
    -0.25
    åĭĩæ°Ķ
    -0.25
    TableModel
    -0.25
    æĻĤçĤ¹ãģ§
    -0.25
    POSITIVE LOGITS
    åĪĨ离
    0.27
    sein
    0.26
     repl
    0.26
    å¾Ĥ
    0.25
     infer
    0.25
     unre
    0.25
    åıĹåĪ°
    0.25
    ä¸Ģ线
    0.25
    RIPT
    0.24
    ofil
    0.24
    Activations Density 11.919%

    No Known Activations