© 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. 8818
    Prev
    Next
    INDEX
    Explanations

    choosing early, mid, late varieties

    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
    çİ·
    -0.09
    éº»æľ¨
    -0.08
    èį§
    -0.08
    æµ·åºķ
    -0.08
    纯æ´ģ
    -0.08
    å·Ŀ
    -0.08
    éĿĴèĽĻ
    -0.08
    é²Ľ
    -0.07
    ä¸īæĿ¡
    -0.07
    ewed
    -0.07
    POSITIVE LOGITS
    åŁ¹èĤ²
    0.13
    åľŁå£¤
    0.13
    ç§įæ¤į
    0.12
    æł½åŁ¹
    0.12
    æµĩæ°´
    0.11
    åĽŃ
    0.11
    åŃ£èĬĤ
    0.11
    åħ»æĬ¤
    0.11
    ç¹ģæ®ĸ
    0.11
    éĺ³åı°
    0.10
    Activations Density 0.058%

    No Known Activations