© 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. 51647
    Prev
    Next
    INDEX
    Explanations

    second or third

    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
    çıī
    -0.11
    å¹³åĿĩæ°´å¹³
    -0.10
    éĹ´éļĻ
    -0.09
    ìĹŃ
    -0.09
    èĩªåįij
    -0.09
    ses
    -0.09
    éĹªéĹª
    -0.09
    欢è¿İæĤ¨
    -0.09
    åĿĩæľī
    -0.08
    çı§
    -0.08
    POSITIVE LOGITS
    æѤ类
    0.10
    -ever
    0.10
    ä»»ä½ķå½¢å¼ı
    0.09
     веÑī
    0.09
    èį¼
    0.09
    icity
    0.09
    èĬ±æľµ
    0.09
    åħħ满
    0.08
    oline
    0.08
    fte
    0.08
    Activations Density 0.051%

    No Known Activations