© 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. 52239
    Prev
    Next
    INDEX
    Explanations

    advocacy and advocating for others

    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
    mates
    -0.09
    ingly
    -0.09
    è¯Ŀ说
    -0.08
    çĵ¯
    -0.08
    åıijå±ķ壮大
    -0.08
    nga
    -0.08
    ton
    -0.08
    lda
    -0.08
    maker
    -0.08
    ä½ĵä¼ļ
    -0.08
    POSITIVE LOGITS
    ðŁı»
    0.12
    ðŁı¼
    0.11
    ancement
    0.10
    itat
    0.09
    们éĥ½
    0.09
    ষ
    0.09
    ement
    0.09
    iveness
    0.09
    æĢ§å¼º
    0.09
    ·
    0.09
    Activations Density 0.008%

    No Known Activations