© 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. 22882
    Prev
    Next
    INDEX
    Explanations

    marriage and divorce

    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
     Dich
    -0.11
    è¿Ŀè§Ħ
    -0.09
    erro
    -0.09
     dich
    -0.09
    =find
    -0.09
    leftright
    -0.09
    MAND
    -0.09
    yk
    -0.09
     transported
    -0.08
    _EXCEPTION
    -0.08
    POSITIVE LOGITS
    æīĭç»Ń
    0.12
    åĬŀçIJĨ
    0.12
    辦çIJĨ
    0.10
     divorce
    0.10
    离å©ļ
    0.10
    èĶļ
    0.10
    æĮĤåı·
    0.09
    æ°ijæĶ¿å±Ģ
    0.09
    é¢Ĩåıĸ
    0.09
    å®ķ
    0.09
    Activations Density 0.035%

    No Known Activations