© 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. 6815
    Prev
    Next
    INDEX
    Explanations

    Years

    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
    rop
    -0.27
    ','%
    -0.25
    ·¨
    -0.25
    mun
    -0.24
    earing
    -0.24
    ous
    -0.24
    å¤ļç§įå½¢å¼ı
    -0.24
    æł¹æį®ä¸įåIJĮ
    -0.24
    å½ĵæĹ¥
    -0.24
    thy
    -0.24
    POSITIVE LOGITS
    人æ°Ķ
    0.27
    ernals
    0.25
    hind
    0.25
    çªĴæģ¯
    0.25
     !$
    0.25
    代è¨Ģ
    0.24
    æIJª
    0.23
    çİ·
    0.23
    ADO
    0.23
    зд
    0.23
    Activations Density 0.023%

    No Known Activations