© 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. 9014
    Prev
    Next
    INDEX
    Explanations

    fructose

    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
    ELS
    -0.11
    èĢģé¾Ħ
    -0.10
    adin
    -0.09
    ä¿ĿçķĻ
    -0.09
    裸
    -0.09
     resend
    -0.08
    åĽŀé¦ĸ
    -0.08
    æīĢåľ¨
    -0.08
    å¡ŀ
    -0.08
     Dzi
    -0.08
    POSITIVE LOGITS
    uctose
    0.10
    æĸĩåĮĸä¼łæĴŃ
    0.10
    éĻĮ
    0.10
    áb
    0.10
    éĢ¢
    0.09
    èĤĩ
    0.09
    飦
    0.09
    èĶĹ
    0.09
    ç»Ĵ
    0.09
    UID
    0.09
    Activations Density 0.084%

    No Known Activations