© 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. 142775
    Prev
    Next
    INDEX
    Explanations

    Code/technical text

    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
    sing
    -0.34
    signup
    -0.28
    æµģè¡Į
    -0.27
     sing
    -0.27
    .Criteria
    -0.26
    .Firebase
    -0.24
     GLES
    -0.24
    æµģè¡ĮçļĦ
    -0.24
     incumb
    -0.24
    stu
    -0.24
    POSITIVE LOGITS
    {}",
    0.28
    TemplateName
    0.27
    è¿ĺæĺ¯è¦ģ
    0.26
    enton
    0.26
    ><![
    0.26
    .navigate
    0.26
    ersistent
    0.26
    zte
    0.25
    lix
    0.24
    请åıĬæŶ
    0.24
    Activations Density 4.919%

    No Known Activations