© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 141236
    Prev
    Next
    INDEX
    Explanations

    programming

    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
    Not in Any Lists

    No Comments

    Negative Logits
     turned
    -0.29
     again
    -0.29
     backed
    -0.28
    è¯ĭ
    -0.28
    lıkl
    -0.27
    again
    -0.26
    -turned
    -0.26
     webdriver
    -0.25
    åĨį次
    -0.25
     ammon
    -0.25
    POSITIVE LOGITS
    èĩĨ
    0.30
    thood
    0.29
     frei
    0.27
     unanimous
    0.25
    æĦ¿æľĽ
    0.25
    ophon
    0.25
    OrFail
    0.25
    ETHOD
    0.25
    xmlns
    0.24
    esser
    0.24
    Activations Density 43.459%

    No Known Activations