© 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. 20524
    Prev
    Next
    INDEX
    Explanations

    ban or moratorium

    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
    NAL
    -0.10
    åѤ
    -0.10
    沪
    -0.09
    èĵĿ天
    -0.09
    æłĩæĿĨ
    -0.09
    åģļ
    -0.08
    çħĬ
    -0.08
    第ä¸ī次
    -0.08
    èĤĽ
    -0.08
    ä¸įç»ıæĦı
    -0.08
    POSITIVE LOGITS
    éĻIJåĪ¶
    0.14
    ç¦ģ
    0.13
    ban
    0.13
     ban
    0.13
    ç¦ģæŃ¢
    0.12
     bans
    0.12
    æļĤåģľ
    0.11
    åħ¨éĿ¢
    0.11
     restrictions
    0.10
    _restrict
    0.10
    Activations Density 0.060%

    No Known Activations