© 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. 51832
    Prev
    Next
    INDEX
    Explanations

    pigment, color, opacity, primary colors

    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
    åħĪè¿Ľåįķä½į
    -0.09
     ÑĢеÑĪил
    -0.09
    æīĢåľ¨åľ°
    -0.09
    iasi
    -0.09
    ç¥ļ
    -0.09
    èĪĴ
    -0.09
    å®ļä½į
    -0.09
    ç¬ijèĦ¸
    -0.08
    NSE
    -0.08
    å¥īçĮ®
    -0.08
    POSITIVE LOGITS
    é¢ľ
    0.11
    çī¹æ®ĬçļĦ
    0.09
    æłijèĦĤ
    0.09
    ä¸ĢèĦļ
    0.09
     pigment
    0.09
    åºķçĽĺ
    0.09
    åį´åıijçİ°
    0.09
    à¹Ģà¸Ī
    0.08
    纵
    0.08
    ierz
    0.08
    Activations Density 0.057%

    No Known Activations