© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 7310
    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
     nab
    -0.31
    åį¡
    -0.28
    udos
    -0.27
    ypi
    -0.27
    oca
    -0.27
    æľĶ
    -0.25
    ONTAL
    -0.24
    eca
    -0.24
    овиÑĩ
    -0.23
    对æ¯Ķ
    -0.23
    POSITIVE LOGITS
    Īĺ
    0.26
    欢è¿İæĤ¨
    0.25
    çļĦ第ä¸Ģ个
    0.25
    çķĮ第ä¸Ģ
    0.25
    é©¿ç«Ļ
    0.24
    è´¹çİĩ
    0.24
    ä¸ĩ家
    0.24
     hamm
    0.23
    å¶Ĥ
    0.23
     strained
    0.23
    Activations Density 0.123%

    No Known Activations

    This feature has no known activations.