© 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. 14-TRANSCODER-HP
    7. 40787
    Prev
    Next
    INDEX
    Explanations

    European countries

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ="__
    -0.29
    顶
    -0.24
     slik
    -0.24
    æݨ
    -0.24
    apo
    -0.23
    ereo
    -0.23
     dword
    -0.23
    urse
    -0.23
     unequal
    -0.23
    ==$
    -0.23
    POSITIVE LOGITS
    è¿ĻäºĽäºº
    0.27
    Categories
    0.27
    odel
    0.26
    误解
    0.26
    aret
    0.26
    çĵł
    0.25
    å·®ä¸įå¤ļ
    0.24
    eneral
    0.24
    åıĤèĢĥèµĦæĸĻ
    0.24
    失误
    0.24
    Activations Density 1.417%

    No Known Activations