© 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. 51425
    Prev
    Next
    INDEX
    Explanations

    sexuality and biology

    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
     sliding
    -0.09
    æĹłèģĬ
    -0.08
    cdr
    -0.08
    åĨ³
    -0.08
    eker
    -0.08
    èĥĮåIJİçļĦ
    -0.08
    ä¸ī峡
    -0.08
    éĢļéģĵ
    -0.08
     dred
    -0.08
    èĥĮåIJİ
    -0.08
    POSITIVE LOGITS
    æµĬ
    0.11
    unar
    0.09
    容è²Į
    0.09
    icho
    0.09
    éĽ¨æ°´
    0.09
    çĪ½
    0.09
    æĥĬ
    0.08
    å·¥ä¸ļåĮĸ
    0.08
    æĹ¥æ¸IJ
    0.08
    ç²
    0.08
    Activations Density 0.139%

    No Known Activations