© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8710
    Prev
    Next
    INDEX
    Explanations

    refers to

    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
    åı¶åŃIJ
    -0.09
    å¼ķæĿ¥
    -0.09
    åijµ
    -0.09
    кÑĥÑĢ
    -0.09
    eer
    -0.09
    æĢİ
    -0.09
     Zuk
    -0.09
    olas
    -0.08
    à¸ĭะ
    -0.08
    鸳
    -0.08
    POSITIVE LOGITS
    å¾ĹçĽĬ
    0.09
    ibo
    0.09
    å°ĺ
    0.09
    帳
    0.09
    å¥ij
    0.09
    езн
    0.09
    æ°ĶåĢĻ
    0.09
    è¾¹éĻħ
    0.08
    resher
    0.08
    aj
    0.08
    Activations Density 0.123%

    No Known Activations