© 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. 27-TRANSCODER-HP
    7. 57491
    Prev
    Next
    INDEX
    Explanations

    output

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ill
    -0.29
    飶
    -0.27
     while
    -0.26
    åıįæĺłåĩº
    -0.25
    缺å°ij
    -0.25
    贯穿
    -0.25
    åIJ¬å¾Ĺ
    -0.25
    åģļ人
    -0.24
     afford
    -0.24
    cho
    -0.24
    POSITIVE LOGITS
    ä¹Łåı¯èĥ½
    0.34
    ä¹Łå¼Ģå§ĭ
    0.34
    ä¹Łåľ¨
    0.32
     also
    0.32
    产ä¸ļåįĩ级
    0.30
    ä¹Łæĺ¯å¦ĤæѤ
    0.30
    olum
    0.30
    ä¹Łæĺ¯éĿŀ常
    0.30
    ä¹Łä¼ļ
    0.29
     également
    0.29
    Activations Density 0.002%

    No Known Activations