© 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. 21270
    Prev
    Next
    INDEX
    Explanations

    doing it or finding a way

    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
    æ¾Ħ
    -0.09
    éļĶéŁ³
    -0.09
    墩
    -0.09
    åıijèĤ²
    -0.08
    éĶħ
    -0.08
    èĢ·
    -0.08
    è¥Ħ
    -0.08
    uan
    -0.08
    çļĦçĶŁåij½
    -0.08
    ä»·ä½į
    -0.08
    POSITIVE LOGITS
    åģļæ³ķ
    0.11
    åİŁæĿ¥
    0.11
    åİŁæĿ¥æĺ¯
    0.09
    è¡Įäºĭ
    0.09
    åıįèĢĮ
    0.09
    æłĩåĩĨ
    0.09
    çļĦæłĩåĩĨ
    0.09
     solutions
    0.09
    è§ĦèĮĥ
    0.08
    èĬ®
    0.08
    Activations Density 0.133%

    No Known Activations