© 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. 36811
    Prev
    Next
    INDEX
    Explanations

    choosing or picking someone or something

    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
     Lime
    -0.11
    ront
    -0.10
    æݨå´ĩ
    -0.09
    KNOWN
    -0.08
    Enums
    -0.08
    æ®ĭ
    -0.08
    æĸ°å»º
    -0.08
    å¥Ī
    -0.08
    æ²»
    -0.08
    ä¹ħ
    -0.08
    POSITIVE LOGITS
     Ñģебе
    0.10
     اÙĦسÙĦ
    0.09
    ä¸Ģæľµ
    0.09
    æ®ĩ
    0.09
    çģµæ°Ķ
    0.09
    常åĬ¡åī¯
    0.09
    ç³ľ
    0.09
    æį©
    0.09
    åĴĮå®ĮåĸĦ
    0.09
    é£ı
    0.09
    Activations Density 0.040%

    No Known Activations