© 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. 21238
    Prev
    Next
    INDEX
    Explanations

    cast an object

    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
    åĻ±
    -0.09
     ober
    -0.08
    æ¯ĸ
    -0.08
    é»ijæ´ŀ
    -0.08
    ç®Ĺæ³ķ
    -0.08
    çĹ£
    -0.08
    ä¸įå¾Ĺè¶ħè¿ĩ
    -0.08
    èĻļæŀĦ
    -0.08
    omal
    -0.08
     observ
    -0.08
    POSITIVE LOGITS
    ä¼łéĢĴ
    0.10
    对象
    0.10
     AnyObject
    0.10
     пÑĢедÑģÑĤавлÑı
    0.09
    ç±»åŀĭ
    0.09
    icap
    0.09
     scalar
    0.09
    .getObject
    0.09
    .GetObject
    0.09
    å¼ķçĶ¨
    0.09
    Activations Density 1.826%

    No Known Activations