© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 23181
    Prev
    Next
    INDEX
    Explanations

    North, Northern, hemisphere, direction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åı«æĪij
    -0.11
    é¢Ģ
    -0.11
    æĭĨ
    -0.10
    ä¸Ģåı£
    -0.10
    eken
    -0.09
    åĿ¼
    -0.09
    empt
    -0.09
    ç£Ĭ
    -0.09
    levision
    -0.09
    åIJ¦
    -0.09
    POSITIVE LOGITS
     north
    0.10
    åĮĹæĸ¹
    0.10
    åĮĹæŀģ
    0.10
    åĮĹ
    0.10
    north
    0.09
     Northern
    0.09
     pole
    0.09
     northern
    0.09
     North
    0.09
     packs
    0.09
    Activations Density 0.056%

    No Known Activations