© 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. 8484
    Prev
    Next
    INDEX
    Explanations

    debut

    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
    -President
    -0.27
    æĪª
    -0.26
     Vice
    -0.26
     fred
    -0.25
    罪
    -0.25
    éĹ®éĹ®
    -0.25
    verification
    -0.24
    æĹłå¿§
    -0.24
    为éĩįçĤ¹
    -0.23
    翳
    -0.23
    POSITIVE LOGITS
     debut
    0.95
    é¦ĸ
    0.68
     deb
    0.65
    é¦ĸ次
    0.62
     debuted
    0.60
    åĪĿ次
    0.59
     maiden
    0.55
    deb
    0.52
    第ä¸Ģ次
    0.49
    åĪĿ
    0.47
    Activations Density 0.035%

    No Known Activations