© 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. 7650
    Prev
    Next
    INDEX
    Explanations

    Technical questions and answers

    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
    并ä¸įä¼ļ
    -0.38
    并ä¸įèĥ½
    -0.31
    åıªæĺ¯
    -0.30
    并没æľī
    -0.30
    è¿Ļåıªæĺ¯
    -0.28
    åıªæĺ¯ä¸Ģ个
    -0.28
    ä¸įä¼ļæľī
    -0.28
    并ä¸į
    -0.27
    åħ·ä½ĵæĥħåĨµ
    -0.27
    并ä¸įæĺ¯
    -0.26
    POSITIVE LOGITS
    xon
    0.29
     midi
    0.28
    mouth
    0.27
    æŃ¡
    0.26
     mies
    0.26
     ähnlich
    0.26
    ä¸įçŁ¥ä¸į
    0.26
    é»ijæļĹ
    0.25
    èµ·äºĨ
    0.25
    è°ļ
    0.24
    Activations Density 0.026%

    No Known Activations