© 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. 9064
    Prev
    Next
    INDEX
    Explanations

    Chinese characters

    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
    èĵij
    -0.27
     ped
    -0.26
    Ãłng
    -0.26
    Cop
    -0.26
    æ£į
    -0.26
    azole
    -0.25
    acam
    -0.25
    åºĶæľīçļĦ
    -0.25
     unh
    -0.25
    iola
    -0.24
    POSITIVE LOGITS
    说å¾Ĺ
    0.43
    æīĵå¾Ĺ
    0.29
    èµ°å¾Ĺ
    0.27
    çľĭå¾Ĺ
    0.26
    é¢ĸ
    0.26
    rike
    0.25
    åIJĥå¾Ĺ
    0.25
    纵
    0.25
    宣
    0.25
    å¯Ĩ
    0.25
    Activations Density 0.004%

    No Known Activations