© 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. 21055
    Prev
    Next
    INDEX
    Explanations

    index jobs

    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
    æĶ¾æīĭ
    -0.11
    çĤ¸
    -0.09
    身边
    -0.09
     hôm
    -0.09
    æĪIJçĨŁ
    -0.09
    èİĨ
    -0.09
    çĤľ
    -0.09
    æ¸ļ
    -0.09
    ç»°
    -0.09
    ç»Ļä½łä»¬
    -0.09
    POSITIVE LOGITS
    æĶ¶å½ķ
    0.11
    åħ³éĶ®è¯į
    0.10
    饥饿
    0.10
     keyword
    0.09
     conscient
    0.09
     caches
    0.09
    çĵľ
    0.09
    pute
    0.09
    åı¯è§ģ
    0.08
    عÙĤ
    0.08
    Activations Density 0.106%

    No Known Activations