© 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. 62298
    Prev
    Next
    INDEX
    Explanations

    take over, care of

    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
    åį§
    -0.10
    å¾Īéļ¾
    -0.09
    æĭĪ
    -0.09
    æľĢéļ¾
    -0.09
    ä¸ľè·¯
    -0.08
    æĴĩ
    -0.08
    å¦Ĥæŀľä¸įæĺ¯
    -0.08
    æĬķ稿
    -0.08
    å¤ĩ
    -0.08
    antee
    -0.08
    POSITIVE LOGITS
    æ¯ĶæĪij
    0.13
    åİ»åģļ
    0.11
    èĩªæľī
    0.11
    uffs
    0.10
    íķĺëıĦë¡Ŀ
    0.10
    ä»ĸèĩªå·±
    0.10
    樯
    0.09
     Mess
    0.09
    ä¸ĩä¸Ģ
    0.09
    elmet
    0.09
    Activations Density 0.035%

    No Known Activations