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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 31361
    Prev
    Next
    INDEX
    Explanations

    abbreviations followed by verbs or nouns

    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
    人åĿĩ
    -0.09
    æľºåĻ¨
    -0.09
    çĶŁäº§è½¦éĹ´
    -0.09
    cept
    -0.09
    ItemList
    -0.09
    мÑı
    -0.08
    äºī龸
    -0.08
    å·¥åİĤ
    -0.08
    onen
    -0.08
    ãģıãĤĬ
    -0.08
    POSITIVE LOGITS
    çĿĢä»ĸ
    0.11
    æ¹ĸåĮº
    0.09
    ä¸ĩæĪ·
    0.09
    第ä¸ĥ
    0.08
    åĮ¡
    0.08
     lore
    0.08
    å®ľå±ħ
    0.08
    夷
    0.08
     prelim
    0.08
    åķ¸
    0.08
    Activations Density 0.137%

    No Known Activations