© 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. 8535
    Prev
    Next
    INDEX
    Explanations

    fighting and victory outcomes

    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
    æ³ķå®ĺ
    -0.10
    ä¼ı
    -0.09
    ÑĢин
    -0.09
    çĭ¬è§Ĵåħ½
    -0.09
    éĿĴéĵľ
    -0.08
    åĮ»åĬ¡äººåijĺ
    -0.08
    ÙĨÙĬ
    -0.08
    æŃ£å¸¸
    -0.08
    باط
    -0.08
    ä¹ħ
    -0.08
    POSITIVE LOGITS
    æ¸Ĭ
    0.10
    çĵľ
    0.09
    å·½
    0.09
    åĽ½åĬ¡
    0.09
     Emerson
    0.09
    è¢
    0.09
    èĵģ
    0.08
    èĵĵ
    0.08
    å¨ģèĥģ
    0.08
     Wellington
    0.08
    Activations Density 0.036%

    No Known Activations