© 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. 4746
    Prev
    Next
    INDEX
    Explanations

    the

    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
    è¿Ļ两个
    -0.33
    为æĤ¨æıIJä¾Ľ
    -0.31
    è¿Ļ两
    -0.29
    è¿Ļ两ç§į
    -0.28
    å·¦åı³
    -0.28
    两ä½į
    -0.26
    åīįåIJİ
    -0.26
     neither
    -0.26
     two
    -0.26
    .spi
    -0.26
    POSITIVE LOGITS
    åı¦ä¸Ģ
    0.38
     counterpart
    0.36
    åIJĮä¼´
    0.34
     partnered
    0.32
     companion
    0.32
     partner
    0.32
    éħįå¥Ĺ
    0.30
    åı¦ä¸Ģ个
    0.30
    åı¦ä¸Ģç§į
    0.30
     accomp
    0.29
    Activations Density 0.057%

    No Known Activations