© 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. 3571
    Prev
    Next
    INDEX
    Explanations

    not necessarily

    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
    èĢĮä¸įæĺ¯
    -0.15
    èĢĮéĿŀ
    -0.14
    并ä¸į
    -0.12
     não
    -0.12
     nicht
    -0.11
    ä¸įåĩº
    -0.11
    èĢĮä¸į
    -0.11
     не
    -0.11
     not
    -0.11
    ä¸įäºĨ
    -0.11
    POSITIVE LOGITS
    æľīä»»ä½ķ
    0.25
     necessarily
    0.24
     anymore
    0.23
     سÙĪÙī
    0.20
    ä»»ä½ķ人
    0.18
     há»ģ
    0.17
    ä¹Łä¸įåı¯èĥ½
    0.17
    ä¸Ŀ毫
    0.17
    éĤ£ä¹Ī容æĺĵ
    0.16
    زاÙĦ
    0.16
    Activations Density 1.118%

    No Known Activations