© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51402
    Prev
    Next
    INDEX
    Explanations

    women, woman, judges, marriage, progress

    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
    ÑģÑĤÑĭ
    -0.10
    åIJİæŀľ
    -0.09
    éĥ½å¸Ĥ
    -0.09
    æĺŃ
    -0.09
    æĬĬè¿ĻäºĽ
    -0.09
    å§ĭäºİ
    -0.09
    ainties
    -0.09
    urray
    -0.09
    羡
    -0.09
    禳
    -0.09
    POSITIVE LOGITS
    åľ¨åĵª
    0.10
    ä¹ĭ人
    0.09
    ä¹±
    0.08
    ocha
    0.07
    ани
    0.07
    .aut
    0.07
    åħĦå¼Ł
    0.07
    å¼ĢéŨ
    0.07
    bern
    0.07
    asd
    0.07
    Activations Density 0.035%

    No Known Activations