© 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. 9170
    Prev
    Next
    INDEX
    Explanations

    violence, riot, protests

    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
    _tp
    -0.09
    åIJĮè¡Į
    -0.08
    itles
    -0.08
    主è§Ĥ
    -0.08
    åĿı
    -0.08
    quiz
    -0.08
    æĹĭ
    -0.08
    çķĭ
    -0.08
    eur
    -0.08
    IRST
    -0.08
    POSITIVE LOGITS
    æļ´åĬĽ
    0.11
    èĶĵ延
    0.10
    çĪĨåıij
    0.10
    éĹ¹
    0.10
    éªļ
    0.09
    è¡Ĺ头
    0.09
    械
    0.09
    æĥħ绪
    0.09
    å¹³éĿĻ
    0.09
    åľºéĿ¢
    0.09
    Activations Density 0.088%

    No Known Activations