© 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. 2713
    Prev
    Next
    INDEX
    Explanations

    email addresses

    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
    è·µ
    -0.10
    纶
    -0.10
    озв
    -0.10
    åĨµ
    -0.09
    å¹½
    -0.09
    æľ½
    -0.09
    æ´¥
    -0.09
    auce
    -0.09
    æĺ¼å¤ľ
    -0.09
    åħ¨æĹ¥åĪ¶
    -0.09
    POSITIVE LOGITS
    ç²Ĺ
    0.09
    身边
    0.08
    ä¸įçĦ¶
    0.07
    ÑĢин
    0.07
    ather
    0.07
    ż
    0.07
    åĮĢ
    0.07
     breakup
    0.07
     Barber
    0.07
    çij±
    0.07
    Activations Density 0.001%

    No Known Activations