© 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. 22746
    Prev
    Next
    INDEX
    Explanations

    couple, duo, pairs, roles

    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
     Boys
    -0.10
     boys
    -0.10
    å°ıä¼ĻåŃIJ
    -0.10
     Brothers
    -0.08
    arel
    -0.08
    boys
    -0.08
    baugh
    -0.08
    åıł
    -0.08
    vecs
    -0.08
     pockets
    -0.08
    POSITIVE LOGITS
    夫妻
    0.14
    åIJĦèĩª
    0.14
    åıĮåıĮ
    0.14
    夫å¦ĩ
    0.13
     couple
    0.11
    ä¼ī
    0.11
    å¾Ĺ天
    0.11
    çĶ·å¥³
    0.11
     themselves
    0.11
    åħ±åIJĮ
    0.11
    Activations Density 0.165%

    No Known Activations