© 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. 8110
    Prev
    Next
    INDEX
    Explanations

    extended . / of aries increment

    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
    æ²¹èħ»
    -0.09
    lei
    -0.08
    è
    -0.08
    Spoiler
    -0.08
    该éĻ¢
    -0.08
    (Token
    -0.08
    åĪĨ级
    -0.08
    é»ı
    -0.07
    .ping
    -0.07
    æľ¬èº«å°±æĺ¯
    -0.07
    POSITIVE LOGITS
    è¿Ļåıª
    0.10
    绣
    0.09
    rita
    0.09
    åĪĿ次
    0.09
    顽
    0.08
     extended
    0.08
    举缣
    0.08
    éļĨ
    0.08
    Extended
    0.08
     Flesh
    0.08
    Activations Density 0.002%

    No Known Activations