© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 53267
    Prev
    Next
    INDEX
    Explanations

    tide, moon, spring, forces, high, cause

    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
    æĸĹ
    -0.10
    éĻį
    -0.09
    è¹Ģ
    -0.09
    çĦ°
    -0.09
    éĶĻè¿ĩäºĨ
    -0.09
    åĴĮå®ĮåĸĦ
    -0.08
    å¤į
    -0.08
    é£
    -0.08
    éľ¹
    -0.08
     Lawson
    -0.08
    POSITIVE LOGITS
    æ½®
    0.11
     tide
    0.10
    浪潮
    0.10
    樽
    0.10
    æµ·æ´ĭ
    0.09
    ä¸ī项
    0.09
    çļİ
    0.09
    æµ·æ°´
    0.09
    Moon
    0.09
    æĵį
    0.09
    Activations Density 0.030%

    No Known Activations