© 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. 20878
    Prev
    Next
    INDEX
    Explanations

    affiliate links

    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
    æīĭæİĮ
    -0.08
     Cliff
    -0.08
    eming
    -0.08
    çļĦçľ¼çĿĽ
    -0.08
    梳
    -0.08
    æIJģ
    -0.08
    .ol
    -0.08
    碲
    -0.08
    ç¥Ģ
    -0.08
     innocent
    -0.07
    POSITIVE LOGITS
    缴åįĩ
    0.09
    èĬĹ
    0.09
     Tal
    0.09
    à¸Ħะ
    0.09
    hound
    0.09
    athi
    0.08
    ä»İ容
    0.08
    åĨ°ç®±
    0.08
    é£İåı£
    0.08
    ä¸Ī夫
    0.08
    Activations Density 0.031%

    No Known Activations