© 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. 19-TRANSCODER-HP
    7. 8229
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ä¸įåĥı
    -0.30
     mate
    -0.28
    èĢĮä¸įæĺ¯
    -0.27
    ot
    -0.27
    è¿Ļç§įæĸ¹å¼ı
    -0.26
    ä¸į符
    -0.25
    人们对
    -0.24
    king
    -0.24
     civilized
    -0.24
    第äºĮå±Ĭ
    -0.24
    POSITIVE LOGITS
    çĤ¹å¤´
    0.30
    深深
    0.27
    gren
    0.27
    azole
    0.26
    awai
    0.25
     factorial
    0.25
    ieber
    0.25
    crow
    0.25
     crow
    0.24
    COPE
    0.24
    Activations Density 0.047%

    No Known Activations

    This feature has no known activations.