© 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. 30820
    Prev
    Next
    INDEX
    Explanations

    biomedical science and mathematics classifications

    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
    ä¸įä½ı
    -0.09
    æł¡åĽŃ
    -0.08
    è¦ģåģļåĪ°
    -0.08
    -campus
    -0.08
     campus
    -0.08
    æ®Ħ
    -0.08
    _PTR
    -0.08
     Bakery
    -0.08
    å¤ĩ份
    -0.08
     Plain
    -0.08
    POSITIVE LOGITS
    èĥ½çľĭåĪ°
    0.09
    åħ·ä½ĵçļĦ
    0.09
    äºļè¿IJ
    0.09
    éĺľ
    0.08
    æĹŃ
    0.08
    äºļè¿IJä¼ļ
    0.08
    sumer
    0.08
     Ingram
    0.08
    Specific
    0.08
    endale
    0.08
    Activations Density 0.045%

    No Known Activations