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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 4988
    Prev
    Next
    INDEX
    Explanations

    Code and special characters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cheek
    -0.26
    ativo
    -0.26
    atif
    -0.24
    åŀĽ
    -0.24
     AC
    -0.24
     Checker
    -0.23
    çłĸ
    -0.23
    -ac
    -0.23
     decoder
    -0.23
    thora
    -0.23
    POSITIVE LOGITS
    andes
    0.27
     cust
    0.26
    hop
    0.25
    cust
    0.24
    å·´å·´
    0.24
    è¿Ļ款车
    0.24
     ros
    0.23
    bery
    0.23
     Chapman
    0.23
     ITE
    0.23
    Activations Density 0.004%

    No Known Activations