© 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. 50789
    Prev
    Next
    INDEX
    Explanations

    continue with condition

    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
    -0.10
    ä¸įèĥ½åĨį
    -0.10
    rosso
    -0.08
    欲
    -0.08
     now
    -0.08
    ä»Ĭãģ¯
    -0.08
     ÑĤепеÑĢÑĮ
    -0.08
    now
    -0.08
    è²Įä¼¼
    -0.08
    çªģåĩº
    -0.08
    POSITIVE LOGITS
    åıªä¼ļ
    0.10
    æ°¸è¿ľ
    0.10
    å°±ä¼ļ
    0.10
    å°±ä¸įä¼ļ
    0.10
    被æ·ĺæ±°
    0.10
    æ°¸éģł
    0.09
     forever
    0.09
     mãi
    0.09
    èĨı
    0.09
    å°±æľĥ
    0.09
    Activations Density 0.068%

    No Known Activations