© 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. 39256
    Prev
    Next
    INDEX
    Explanations

    third party partners

    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
     Orig
    -0.09
    å®ľ
    -0.09
    大æĪ·
    -0.09
    æľīå¾Ī大
    -0.08
    å¤ļä½ĻçļĦ
    -0.08
    ouns
    -0.08
    اÙĦØ·
    -0.08
    ä¸Ģ个æĺŁæľŁ
    -0.08
    æŁ¥æĺİ
    -0.08
    ä¸Ń举
    -0.08
    POSITIVE LOGITS
    ä¼Ļ
    0.10
    åħ±åIJĮä½ĵ
    0.10
    å®ķ
    0.09
    å§Ķæīĺ
    0.09
    ç»ĨèĬĤ
    0.09
     Sharing
    0.08
    Sharing
    0.08
    éħ£
    0.08
    ä»Ħ
    0.08
    èij¡
    0.08
    Activations Density 0.019%

    No Known Activations