© 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. 52124
    Prev
    Next
    INDEX
    Explanations

    more

    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
    å¾Īæ£Ĵ
    -0.10
    parency
    -0.10
    ä»Ģä¹Īä¸ľè¥¿
    -0.10
    å½Ŀ
    -0.10
    æ³¼
    -0.09
    éĩijåĪļ
    -0.09
    /xhtml
    -0.09
     Tok
    -0.09
    æľīè¿ĩ
    -0.09
    inkel
    -0.09
    POSITIVE LOGITS
    éĺĻ
    0.10
    é¢Ĩä¼ļ
    0.09
     about
    0.09
    è¿Ļæĺ¯åĽłä¸º
    0.09
    ä»Ĭ天çļĦ
    0.08
    iren
    0.08
    orative
    0.08
    身边
    0.08
    fabs
    0.08
    ieÅĦ
    0.08
    Activations Density 0.014%

    No Known Activations