© 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. 8787
    Prev
    Next
    INDEX
    Explanations

    nestled in or on

    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
    æĮ¯
    -0.10
    åįĥéĩĮ
    -0.09
    çĦ¦
    -0.08
    è¿ĩ硬
    -0.08
    chest
    -0.08
    樽
    -0.08
    obic
    -0.08
    西æ´ĭ
    -0.08
    èĪ¶
    -0.08
    çĺĹ
    -0.08
    POSITIVE LOGITS
    èĥ¥
    0.11
    wares
    0.10
    avar
    0.09
    éķ¶åµĮ
    0.09
    ви
    0.09
    åįĬå²Ľ
    0.09
    æ°ĵ
    0.09
    滨
    0.08
    åĿIJèIJ½åľ¨
    0.08
    åŃļ
    0.08
    Activations Density 0.038%

    No Known Activations