© 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. 8172
    Prev
    Next
    INDEX
    Explanations

    censorship and interference

    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
    è¿
    -0.10
    cole
    -0.09
    æĻı
    -0.09
    ç«ĭ足
    -0.09
    nodoc
    -0.09
    .twitter
    -0.08
    æĿ¾å¼Ľ
    -0.08
    ä»ģ
    -0.08
    çģ¿
    -0.08
    à¸ģรรม
    -0.08
    POSITIVE LOGITS
     censorship
    0.18
     censor
    0.17
    éĴ³
    0.14
    åİĭåĪ¶
    0.13
    åĻ¤
    0.12
    ç¦ģåĮº
    0.11
    åİĭæĬij
    0.11
     stif
    0.10
    æĿŁç¼ļ
    0.10
    åīĬ
    0.10
    Activations Density 0.093%

    No Known Activations