© 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. 129049
    Prev
    Next
    INDEX
    Explanations

    period

    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
     nuts
    -0.28
    hea
    -0.28
    opr
    -0.28
    eve
    -0.27
    çī
    -0.27
    ion
    -0.27
    ioni
    -0.26
    sink
    -0.26
     sink
    -0.26
    ION
    -0.26
    POSITIVE LOGITS
    åĨĮ
    0.28
    sume
    0.27
     nämlich
    0.26
    à¸ļà¸Ĺ
    0.26
    asters
    0.26
     prefixes
    0.23
    ↵        ↵        ↵
    0.23
    äºĨæĪijçļĦ
    0.23
    enses
    0.23
    holds
    0.23
    Activations Density 10.484%

    No Known Activations