© 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. 52765
    Prev
    Next
    INDEX
    Explanations

    open world adventure

    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
    åħ¬æĬ¥
    -0.10
    çīŁ
    -0.09
    å£ķ
    -0.09
    èĥ½åĬĽå¼º
    -0.09
    æ®Ĩ
    -0.09
    ä¼ĺåĬ¿
    -0.09
    cott
    -0.09
    éľŃ
    -0.09
     eagle
    -0.09
     Albuquerque
    -0.09
    POSITIVE LOGITS
    çīĮ
    0.10
    åįĹè·¯
    0.10
    äºĪ
    0.09
    æģ¢
    0.09
    ä¿
    0.09
    å®ı
    0.08
    æĬ±
    0.08
    bell
    0.08
    åįģä¸ĩ
    0.08
    è¡Ģ
    0.08
    Activations Density 0.113%

    No Known Activations