© 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. 63722
    Prev
    Next
    INDEX
    Explanations

    cancer

    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
    ==========↵
    -0.25
     Readonly
    -0.25
     raining
    -0.25
     overwhelming
    -0.25
    PARATOR
    -0.24
     PLUS
    -0.24
    OMEM
    -0.24
     Oaks
    -0.23
     Geh
    -0.23
    _)č↵
    -0.23
    POSITIVE LOGITS
    ä»»ä½ķå½¢å¼ı
    0.27
    éı¡
    0.25
     any
    0.24
    åIJĦè¡ĮåIJĦä¸ļ
    0.24
     AssemblyTitle
    0.24
    tv
    0.24
    kte
    0.24
     seafood
    0.24
     Nos
    0.24
    theses
    0.24
    Activations Density 5.947%

    No Known Activations