© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 6718
    Prev
    Next
    INDEX
    Explanations

    Town Hall

    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
    åĹ½
    -0.10
    ä»İå°ı
    -0.10
    代åĬŀ
    -0.10
    宸
    -0.09
    å¼łæī¬
    -0.09
    èµ°è·¯
    -0.09
    fic
    -0.09
    ãĥĬãĥ«
    -0.08
    æĶĺ
    -0.08
    åĿļ强
    -0.08
    POSITIVE LOGITS
    ä¸ĢåĪ»
    0.09
     Abr
    0.09
    åı
    0.09
    ä¼ļè®®ä¸Ĭ
    0.08
    ues
    0.08
    ourced
    0.08
    ä¸ĢåľĪ
    0.08
    ä¸įçŁ¥ä¸įè§ī
    0.08
    ä¸įçŁ¥ä¸į
    0.08
    Abr
    0.08
    Activations Density 0.002%

    No Known Activations