© 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. 8347
    Prev
    Next
    INDEX
    Explanations

    longest consecutive winning streak

    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
     полно
    -0.11
    ä¸Ģæīĭ
    -0.11
    slash
    -0.09
    åİķ
    -0.09
    avia
    -0.09
    æĭĶ
    -0.09
    éľ²
    -0.09
    zimmer
    -0.09
     Reeves
    -0.09
    æķŀå¼Ģ
    -0.09
    POSITIVE LOGITS
    缴åĪ°
    0.11
    å¾Ĺä¸įåĪ°
    0.11
    è¿Ļä¹Īä¹ħ
    0.10
    éķ¿è¾¾
    0.10
    空çĻ½
    0.09
     longest
    0.09
    å¾Īä¹ħ
    0.09
    itol
    0.09
    å¾Īéķ¿
    0.08
    è¿Łè¿Ł
    0.08
    Activations Density 0.051%

    No Known Activations