© 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. 50080
    Prev
    Next
    INDEX
    Explanations

    organizations and governing bodies

    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
    assis
    -0.09
    ç»ĥ
    -0.09
     flair
    -0.08
    exion
    -0.08
    è®Ń
    -0.08
    æ§IJ
    -0.08
    ë³ij
    -0.08
    elan
    -0.08
    æªĶ
    -0.08
    fst
    -0.08
    POSITIVE LOGITS
    æĸ¼æĺ¯
    0.10
    æĹĹä¸ĭçļĦ
    0.10
    趣
    0.09
    ä¸ĭå±ŀ
    0.09
    пл
    0.09
    ä¹Łå°±æĺ¯è¯´
    0.09
    æĪIJç«ĭ以æĿ¥
    0.09
    æ¶Īè´¹åįĩ级
    0.09
    äºİæĺ¯
    0.09
    åĽ½éĺ²
    0.09
    Activations Density 0.078%

    No Known Activations