© 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. 57368
    Prev
    Next
    INDEX
    Explanations

    feminine gender 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
    åİļåİļ
    -0.09
    æĥĭ
    -0.09
    æĥ¦
    -0.09
    층
    -0.09
    ç³ľ
    -0.09
    åĽ¢è´Ń
    -0.08
    ulin
    -0.08
    liner
    -0.08
    宾
    -0.08
    æī¹éĩı
    -0.08
    POSITIVE LOGITS
    姿åĬ¿
    0.17
    æĬĢå·§
    0.14
    ç»ĥä¹ł
    0.13
    æīĭåĬ¿
    0.13
    çĶ¨æīĭ
    0.13
    åĬ¨ä½ľ
    0.13
    çĨŁç»ĥ
    0.12
    姿
    0.12
     technique
    0.11
    çļĦåĬ¨ä½ľ
    0.11
    Activations Density 0.210%

    No Known Activations