© 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. 64627
    Prev
    Next
    INDEX
    Explanations

    Skills

    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
    æľĽ
    -0.28
    çļĦæĺ¯
    -0.26
    é¦Ļ
    -0.26
    ãĤĭãģ®ãģĮ
    -0.25
    ureau
    -0.25
    ãĢĤ“
    -0.25
     doomed
    -0.25
    çļĦè¯Ŀ
    -0.24
    ä¸ĢæĿ¡é¾Ļ
    -0.24
    XS
    -0.24
    POSITIVE LOGITS
    å½ĵåľ°æĶ¿åºľ
    0.28
     Vert
    0.26
     locally
    0.25
     adj
    0.25
     Atl
    0.24
    çłĶåĪ¤
    0.24
    heits
    0.24
     Genome
    0.23
    -ticket
    0.23
    å½ĵåľ°
    0.23
    Activations Density 1.643%

    No Known Activations