© 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. 8882
    Prev
    Next
    INDEX
    Explanations

    date and time values

    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
    ä¸įçķĻ
    -0.10
    éĢ¼
    -0.09
    æģ¸
    -0.09
    åĪĬçī©
    -0.09
    æ¶ķ
    -0.09
    mond
    -0.09
    ette
    -0.09
     chá»ĭu
    -0.09
    衬
    -0.09
    ãģ«ãģ¤
    -0.09
    POSITIVE LOGITS
    å·²ç»ıæĺ¯
    0.11
    导åħ¥
    0.09
    å·²æĺ¯
    0.09
    CURRENT
    0.08
    æŃ£å¤Ħäºİ
    0.08
    èŁ²
    0.08
    upos
    0.08
    çİ°çĬ¶
    0.08
    .Timestamp
    0.08
    åĩłçĤ¹
    0.08
    Activations Density 0.063%

    No Known Activations