© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 51736
    Prev
    Next
    INDEX
    Explanations

    titles often in quotes

    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
    irim
    -0.09
    侬
    -0.09
    ç¡
    -0.09
    骡
    -0.09
    ughs
    -0.08
     GANG
    -0.08
     kop
    -0.08
    GroupId
    -0.08
    çļĭ
    -0.08
    æīĵæŃ»
    -0.08
    POSITIVE LOGITS
    æ¯Ľ
    0.12
    ashed
    0.09
    æľī害
    0.09
    æĦł
    0.08
    主æĹ¨
    0.08
    æ¼Ķå¥ı
    0.08
    æĭĽ
    0.08
    æĸ½å±ķ
    0.08
    ä¸Ģæīĭ
    0.08
    çļĦåıijçĶŁ
    0.08
    Activations Density 0.101%

    No Known Activations