© 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. 52147
    Prev
    Next
    INDEX
    Explanations

    unconventional, atypical, non-standard

    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
    漪
    -0.10
    åĪ¶åº¦æĶ¹éĿ©
    -0.09
    iek
    -0.09
    çħ
    -0.09
    çĪ¬
    -0.08
    è¿ĺæĺ¯è¦ģ
    -0.08
    èĩªåѦ
    -0.08
    anvas
    -0.08
    ä»İä¸Ń
    -0.08
    碰åĪ°
    -0.08
    POSITIVE LOGITS
     unconventional
    0.10
     ÙĪغÙĬر
    0.10
    çĶ·ä¸»
    0.09
    ä¹ĭ举
    0.09
    æĢª
    0.09
    æīĵçł´äºĨ
    0.09
    -standard
    0.09
    åıijå¸ĥæŶéĹ´
    0.09
    车éģĵ
    0.09
    åŁŃ
    0.09
    Activations Density 0.054%

    No Known Activations