© 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. 21072
    Prev
    Next
    INDEX
    Explanations

    here or this

    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
    å¦Ĥä¸ĭ
    -0.09
    åĶ§
    -0.09
    bote
    -0.09
    quez
    -0.09
     BELOW
    -0.09
    urrencies
    -0.09
    ç¥ĸ
    -0.08
    bles
    -0.08
    ordo
    -0.08
     Brilliant
    -0.08
    POSITIVE LOGITS
    èĢĦ
    0.09
    读åIJİ
    0.09
    å½¼
    0.09
    æĴ¬
    0.08
    ä¸Ģ大
    0.08
    欲
    0.08
    åľ¯
    0.08
    奮
    0.08
    为代表çļĦ
    0.08
    UPDATED
    0.08
    Activations Density 0.079%

    No Known Activations